Merge remote-tracking branch 'origin/dev'

config.yml

@@ -1,57 +1,15 @@
 measurements:
-  - name: arm_length 
-    landmarks: 
-      - 11 
-      - 13 
-      - 15
-
-  - name: leg_length
-    landmarks: 
-      - 23 
-      - 25
-      - 27
-
   - name: shoulder_length
     landmarks:
-      - 11
-      - 12
-
-  - name: neck_to_hip_length
+      - left_shoulder
+      - right_shoulder
+  - name: arm_length
     landmarks:
-      - 11
-      - 23
-
-#0 - nose
-#1 - left eye (inner)
-#2 - left eye
-#3 - left eye (outer)
-#4 - right eye (inner)
-#5 - right eye
-#6 - right eye (outer)
-#7 - left ear
-#8 - right ear
-#9 - mouth (left)
-#10 - mouth (right)
-#11 - left shoulder
-#12 - right shoulder
-#13 - left elbow
-#14 - right elbow
-#15 - left wrist
-#16 - right wrist
-#17 - left pinky
-#18 - right pinky
-#19 - left index
-#20 - right index
-#21 - left thumb
-#22 - right thumb
-#23 - left hip
-#24 - right hip
-#25 - left knee
-#26 - right knee
-#27 - left ankle
-#28 - right ankle
-#29 - left heel
-#30 - right heel
-#31 - left foot index
-#32 - right foot index
-
+      - left_shoulder
+      - left_elbow
+      - left_wrist
+  - name: leg_length
+    landmarks:
+      - left_hip
+      - left_knee
+      - left_ankle

landmarks.js

@@ -0,0 +1,289 @@
+const fs = require("fs");
+const path = require("path");
+const { ArgumentParser } = require("argparse");
+const cv = require("@techstark/opencv-js");
+const yaml = require("js-yaml");
+const { Pose, POSE_LANDMARKS } = require("@mediapipe/pose");
+
+const logging = console;
+const warnings = console;
+
+class Landmarker {
+  static resizedHeight = 256;
+  static resizedWidth = 256;
+
+  constructor() {
+    this.args = this.parseArgs();
+    this.measurements = this.loadLandmarks();
+    if (!this.args.frontImage) {
+      throw new Error("Front image needs to be passed");
+    }
+    if (!this.args.sideImage) {
+      throw new Error("Side image needs to be passed");
+    }
+
+    this.frontImage = cv.imread(this.args.frontImage);
+    this.sideImage = cv.imread(this.args.sideImage);
+
+    this.frontImageResized = cv.resize(
+      this.frontImage,
+      new cv.Size(Landmarker.resizedWidth, Landmarker.resizedHeight),
+    );
+    this.sideImageResized = cv.resize(
+      this.sideImage,
+      new cv.Size(Landmarker.resizedWidth, Landmarker.resizedHeight),
+    );
+
+    this.distances = {};
+
+    this.personHeight = this.args.personHeight;
+    this.pixelHeight = this.args.pixelHeight;
+
+    this.pose = new Pose({
+      locateFile: (file) => {
+        return `https://cdn.jsdelivr.net/npm/@mediapipe/pose/${file}`;
+      },
+    });
+
+    this.landmarksIndices = [
+      POSE_LANDMARKS.LEFT_SHOULDER,
+      POSE_LANDMARKS.RIGHT_SHOULDER,
+      POSE_LANDMARKS.LEFT_ELBOW,
+      POSE_LANDMARKS.RIGHT_ELBOW,
+      POSE_LANDMARKS.LEFT_WRIST,
+      POSE_LANDMARKS.RIGHT_WRIST,
+      POSE_LANDMARKS.LEFT_HIP,
+      POSE_LANDMARKS.RIGHT_HIP,
+      POSE_LANDMARKS.LEFT_KNEE,
+      POSE_LANDMARKS.RIGHT_KNEE,
+      POSE_LANDMARKS.LEFT_ANKLE,
+      POSE_LANDMARKS.RIGHT_ANKLE,
+    ];
+  }
+
+  loadLandmarks() {
+    const file = fs.readFileSync(this.args.yamlFile, "utf8");
+    const landmarksData = yaml.load(file);
+    const measurements = {};
+    for (const measurement of landmarksData.measurements) {
+      measurements[measurement.name] = measurement.landmarks;
+    }
+    return measurements;
+  }
+
+  parseArgs() {
+    const parser = new ArgumentParser({
+      description: "Process images and calculate measurements",
+    });
+    parser.add_argument("--front", {
+      dest: "frontImage",
+      required: true,
+      help: "Path to the front image",
+    });
+    parser.add_argument("--side", {
+      dest: "sideImage",
+      required: true,
+      help: "Path to the side image",
+    });
+    parser.add_argument("--poseDetectionConfidence", {
+      dest: "poseDetectionConfidence",
+      default: 0.5,
+      type: "float",
+      help: "Confidence score for pose detection",
+    });
+    parser.add_argument("--poseTrackingConfidence", {
+      dest: "poseTrackingConfidence",
+      default: 0.5,
+      type: "float",
+      help: "Confidence score for pose tracking",
+    });
+    parser.add_argument("--personHeight", {
+      dest: "personHeight",
+      required: true,
+      type: "int",
+      help: "Person height in cm",
+    });
+    parser.add_argument("--pixelHeight", {
+      dest: "pixelHeight",
+      type: "int",
+      help: "Pixel height of person",
+    });
+    parser.add_argument("--measurement", {
+      dest: "measurement",
+      nargs: "+",
+      type: "str",
+      help: "Type of measurement",
+    });
+    parser.add_argument("--yamlFile", {
+      dest: "yamlFile",
+      required: true,
+      help: "Path to the YAML file containing landmarks",
+    });
+    return parser.parse_args();
+  }
+
+  async run() {
+    await this.pose.initialize();
+    const { frontResults, sideResults } = await this.processImages();
+
+    this.getCenterTopPoint(sideResults);
+
+    const table = [];
+    if (this.args.measurement) {
+      for (const m of this.args.measurement) {
+        if (!this.measurements[m]) {
+          throw new Error("Incorrect input (input not present in config.yml)");
+        } else {
+          const distance = this.calculateDistanceBetweenLandmarks(
+            frontResults,
+            m,
+          );
+          table.push([m, distance]);
+        }
+      }
+    } else {
+      for (const m in this.measurements) {
+        const distance = this.calculateDistanceBetweenLandmarks(
+          frontResults,
+          m,
+        );
+        table.push([m, distance]);
+      }
+    }
+
+    console.table(table);
+
+    this.pose.close();
+  }
+
+  async processImages() {
+    const frontResults = await this.pose.estimatePoses(this.frontImageResized);
+    const sideResults = await this.pose.estimatePoses(this.sideImageResized);
+
+    this.sideImageKeypoints = this.sideImageResized.clone();
+    this.frontImageKeypoints = this.frontImageResized.clone();
+
+    if (frontResults[0].landmarks) {
+      this.drawLandmarks(
+        this.frontImageKeypoints,
+        frontResults[0].landmarks,
+        this.landmarksIndices,
+      );
+    }
+    if (sideResults[0].landmarks) {
+      this.drawLandmarks(
+        this.sideImageKeypoints,
+        sideResults[0].landmarks,
+        this.landmarksIndices,
+      );
+    }
+    return {
+      frontResults: frontResults[0],
+      sideResults: sideResults[0],
+    };
+  }
+
+  pixelToMetricRatio() {
+    const pixelToMetricRatio = this.personHeight / this.pixelHeight;
+    logging.debug("pixelToMetricRatio %s", pixelToMetricRatio);
+    return pixelToMetricRatio;
+  }
+
+  drawLandmarks(image, landmarks, indices) {
+    for (const idx of indices) {
+      const landmark = landmarks[idx];
+      const h = image.rows;
+      const w = image.cols;
+      const cx = Math.round(landmark.x * w);
+      const cy = Math.round(landmark.y * h);
+      this.circle(image, cx, cy);
+    }
+  }
+
+  circle(image, cx, cy) {
+    cv.circle(image, new cv.Point(cx, cy), 2, new cv.Scalar(255, 0, 0), -1);
+  }
+
+  calculateDistanceBetweenLandmarks(frontResults, measurementName) {
+    if (!frontResults.landmarks) {
+      return;
+    }
+
+    const landmarks = frontResults.landmarks;
+    const landmarkNames = this.measurements[measurementName];
+
+    let totalDistance = 0;
+    for (let i = 0; i < landmarkNames.length - 1; i++) {
+      const current = landmarks[landmarkNames[i]];
+      const next = landmarks[landmarkNames[i + 1]];
+      const pixelDistance = this.euclideanDistance(
+        current.x * Landmarker.resizedWidth,
+        current.y * Landmarker.resizedHeight,
+        next.x * Landmarker.resizedWidth,
+        next.y * Landmarker.resizedHeight,
+      );
+      const realDistance = pixelDistance * this.pixelToMetricRatio();
+      totalDistance += realDistance;
+    }
+    return totalDistance;
+  }
+
+  euclideanDistance(x1, y1, x2, y2) {
+    return Math.sqrt((x2 - x1) ** 2 + (y2 - y1) ** 2);
+  }
+
+  getCenterTopPoint(sideResults) {
+    const grayImage = cv.cvtColor(this.sideImageKeypoints, cv.COLOR_BGR2GRAY);
+    const blurredImage = cv.GaussianBlur(grayImage, new cv.Size(5, 5), 0);
+    const roi = blurredImage.roi(
+      new cv.Rect(
+        0,
+        0,
+        this.sideImageResized.cols,
+        Math.floor(this.sideImageResized.rows / 2),
+      ),
+    );
+    this.edges = cv.Canny(roi, 50, 150);
+    const contours = this.edges.findContours(
+      cv.RETR_EXTERNAL,
+      cv.CHAIN_APPROX_SIMPLE,
+    );
+
+    let xt, yt;
+    this.topmostPoint = null;
+
+    for (const contour of contours) {
+      const [xt, yt] = contour.minEnclosingCircle();
+      if (this.topmostPoint === null || yt < this.topmostPoint[1]) {
+        this.topmostPoint = [xt, yt];
+      }
+    }
+
+    const { x, y } = sideResults.landmarks[POSE_LANDMARKS.NOSE];
+    const centerPoint = [
+      x * Landmarker.resizedWidth,
+      y * Landmarker.resizedHeight,
+    ];
+    this.pixelHeight = Math.abs(centerPoint[1] - this.topmostPoint[1]);
+
+    cv.circle(
+      this.sideImageKeypoints,
+      new cv.Point(centerPoint[0], centerPoint[1]),
+      2,
+      new cv.Scalar(255, 0, 0),
+      -1,
+    );
+    cv.circle(
+      this.sideImageKeypoints,
+      new cv.Point(this.topmostPoint[0], this.topmostPoint[1]),
+      2,
+      new cv.Scalar(255, 0, 0),
+      -1,
+    );
+  }
+}
+
+const landmarker = new Landmarker();
+landmarker.run().catch((error) => {
+  console.error(error);
+});

landmarks.py

@@ -1,75 +1,126 @@
-import warnings
+import logging
 import os
+import warnings
+import sys
+os.environ["TF_CPP_MIN_LOG_LEVEL"] = "3"
 from tabulate import tabulate
 import math
 import argparse
 import cv2
-from mediapipe.python.solutions import pose
-import logging
-
-warnings.filterwarnings("ignore",
-                        category=UserWarning,
-                        module="google.protobuf")
-
-os.environ["TF_CPP_MIN_LOG_LEVEL"] = "3"
+from mediapipe.python.solutions import (
+    pose,
+)
+import yaml
+logging.basicConfig(level=logging.INFO)
+warnings.filterwarnings(
+    "ignore",
+    category=UserWarning,
+    module="google.protobuf",
+)
 
+LANDMARK_NAME_TO_INDEX = {
+    "nose": 0,
+    "left_eye_inner": 1,
+    "left_eye": 2,
+    "left_eye_outer": 3,
+    "right_eye_inner": 4,
+    "right_eye": 5,
+    "right_eye_outer": 6,
+    "left_ear": 7,
+    "right_ear": 8,
+    "mouth_left": 9,
+    "mouth_right": 10,
+    "left_shoulder": 11,
+    "right_shoulder": 12,
+    "left_elbow": 13,
+    "right_elbow": 14,
+    "left_wrist": 15,
+    "right_wrist": 16,
+    "left_pinky": 17,
+    "right_pinky": 18,
+    "left_index": 19,
+    "right_index": 20,
+    "left_thumb": 21,
+    "right_thumb": 22,
+    "left_hip": 23,
+    "right_hip": 24,
+    "left_knee": 25,
+    "right_knee": 26,
+    "left_ankle": 27,
+    "right_ankle": 28,
+    "left_heel": 29,
+    "right_heel": 30,
+    "left_foot_index": 31,
+    "right_foot_index": 32,
+}
 
 class Landmarker:
 
     resized_height = 256
-    resized_width = 300
+    resized_width = 256
 
     def __init__(self) -> None:
-        args = self.parse_args()
-        if args.front_image == None:
+        self.args = self.parse_args()
+        self.measurements = self.load_landmarks()
+        if self.args.front_image is None:
             raise Exception("front image needs to be passed")
-        if args.side_image == None:
+        if self.args.side_image is None:
             raise Exception("side image needs to be passed")
 
-        self.front_image = cv2.imread(args.front_image)
-        self.side_image = cv2.imread(args.side_image)
+        self.front_image = cv2.imread(self.args.front_image)
+        self.side_image = cv2.imread(self.args.side_image)
 
-        self.front_image_resized = cv2.resize(
-            self.front_image, (self.resized_height, self.resized_width))
-        self.side_image_resized = cv2.resize(
-            self.side_image, (self.resized_height, self.resized_width))
+        self.front_image_resized = cv2.resize(self.front_image, (self.resized_height, self.resized_width))
+        self.side_image_resized = cv2.resize(self.side_image, (self.resized_height, self.resized_width))
 
         self.distances = {}
 
-        self.person_height = args.person_height
-        self.pixel_height = args.pixel_height
+        self.person_height = self.args.person_height
+        self.pixel_height = self.args.pixel_height
 
         self.pose = pose.Pose(
             static_image_mode=True,
-            min_detection_confidence=args.pose_detection_confidence,
-            min_tracking_confidence=args.pose_tracking_confidence,
+            min_detection_confidence=self.args.pose_detection_confidence,
+            min_tracking_confidence=self.args.pose_tracking_confidence,
         )
-        self.landmarks_to_calculate = []
+
         self.landmarks_indices = [
-            pose.PoseLandmark.LEFT_SHOULDER.value,
-            pose.PoseLandmark.RIGHT_SHOULDER.value,
-            pose.PoseLandmark.LEFT_ELBOW.value,
-            pose.PoseLandmark.RIGHT_ELBOW.value,
-            pose.PoseLandmark.LEFT_WRIST.value,
-            pose.PoseLandmark.RIGHT_WRIST.value,
-            pose.PoseLandmark.LEFT_HIP.value,
-            pose.PoseLandmark.RIGHT_HIP.value,
-            pose.PoseLandmark.LEFT_KNEE.value,
-            pose.PoseLandmark.RIGHT_KNEE.value,
-            pose.PoseLandmark.LEFT_ANKLE.value,
-            pose.PoseLandmark.RIGHT_ANKLE.value,
+            LANDMARK_NAME_TO_INDEX["left_shoulder"],
+            LANDMARK_NAME_TO_INDEX["right_shoulder"],
+            LANDMARK_NAME_TO_INDEX["left_elbow"],
+            LANDMARK_NAME_TO_INDEX["right_elbow"],
+            LANDMARK_NAME_TO_INDEX["left_wrist"],
+            LANDMARK_NAME_TO_INDEX["right_wrist"],
+            LANDMARK_NAME_TO_INDEX["left_hip"],
+            LANDMARK_NAME_TO_INDEX["right_hip"],
+            LANDMARK_NAME_TO_INDEX["left_knee"],
+            LANDMARK_NAME_TO_INDEX["right_knee"],
+            LANDMARK_NAME_TO_INDEX["left_ankle"],
+            LANDMARK_NAME_TO_INDEX["right_ankle"],
         ]
 
+    def load_landmarks(self):
+        with open(self.args.yaml_file, "r") as file:
+            landmarks_data = yaml.safe_load(file)
+        measurements = {}
+        for measurement in landmarks_data["measurements"]:
+            measurements[measurement["name"]] = [LANDMARK_NAME_TO_INDEX[l] for l in measurement["landmarks"]]
+        return measurements
+
     def parse_args(self):
         parser = argparse.ArgumentParser()
-        parser.add_argument("--front",
-                            dest="front_image",
-                            type=str,
-                            help="Front image")
-        parser.add_argument("--side",
-                            dest="side_image",
-                            type=str,
-                            help="Side image")
+        parser.add_argument(
+            "--front",
+            dest="front_image",
+            type=str,
+            help="Front image",
+        )
+        parser.add_argument(
+            "--side",
+            dest="side_image",
+            type=str,
+            help="Side image",
+        )
         parser.add_argument(
             "--pose_detection_confidence",
             dest="pose_detection_confidence",
@@ -86,43 +137,74 @@ class Landmarker:
         )
         parser.add_argument(
             "--person_height",
-            #          default=153,
             dest="person_height",
             type=int,
             help="person height of person",
         )
         parser.add_argument(
             "--pixel_height",
-            #    default=216,
             dest="pixel_height",
             type=int,
             help="pixel height of person",
         )
+        parser.add_argument(
+            "--measurement",
+            dest="measurement",
+            nargs="+",
+            type=str,
+            help="Type of measurement",
+        )
+        parser.add_argument(
+            "--yaml_file",
+            dest="yaml_file",
+            type=str,
+            help="Path to the YAML file containing landmarks",
+        )
         return parser.parse_args()
     
     def run(self):
-
-        logging.warning("person's height: %s", self.person_height)
-
-        logging.warning("person's pixel height: %s", self.pixel_height)
-
-        front_results, side_results = self.process_images()
+        front_results, _ = self.process_images()
 
         self.get_center_top_point(front_results)
 
-        self.calculate_distance_betn_landmarks(front_results)
+        table = []
+        if self.args.measurement:
+            for m in self.args.measurement:
+                if m not in self.measurements:
+                    raise Exception("Incorrect input (input not present in config.yml)")
+                else:
+                    distance = self.calculate_distance_betn_landmarks(front_results, m)
+                    table.append([m, distance])
+        else:
+            for m in self.measurements:
+                distance = self.calculate_distance_betn_landmarks(front_results, m)
+                table.append([m, distance])
 
-        self.output()
-
-        self.display_images()
+        output = tabulate(
+            table,
+            headers=[
+                "measurement",
+                "Distance (cm)",
+            ],
+            tablefmt="plain",
+        )
+        print(output)
 
         self.pose.close()
 
     def process_images(self):
         front_results = self.pose.process(
-            cv2.cvtColor(self.front_image_resized, cv2.COLOR_BGR2RGB))
+            cv2.cvtColor(
+                self.front_image_resized,
+                cv2.COLOR_BGR2RGB,
+            )
+        )
         side_results = self.pose.process(
-            cv2.cvtColor(self.side_image_resized, cv2.COLOR_BGR2RGB))
+            cv2.cvtColor(
+                self.side_image_resized,
+                cv2.COLOR_BGR2RGB,
+            )
+        )
 
         self.side_image_keypoints = self.side_image_resized.copy()
         self.front_image_keypoints = self.front_image_resized.copy()
@@ -139,12 +221,18 @@ class Landmarker:
                 side_results.pose_landmarks,  # type: ignore# type: ignore
                 self.landmarks_indices,
             )
-        return front_results, side_results
+        return (
+            front_results,
+            side_results,
+        )
 
     def pixel_to_metric_ratio(self):
         self.pixel_height = self.pixel_distance * 2
         pixel_to_metric_ratio = self.person_height / self.pixel_height
-        logging.warning("pixel_to_metric_ratio %s", pixel_to_metric_ratio)
+        logging.debug(
+            "pixel_to_metric_ratio %s",
+            pixel_to_metric_ratio,
+        )
         return pixel_to_metric_ratio
 
     def draw_landmarks(self, image, landmarks, indices):
@@ -155,118 +243,85 @@ class Landmarker:
             self.circle(image, cx, cy)
 
     def circle(self, image, cx, cy):
-        return cv2.circle(image, (cx, cy), 2, (255, 0, 0), -1)
+        return cv2.circle(
+            image,
+            (cx, cy),
+            2,
+            (255, 0, 0),
+            -1,
+        )
 
-    def output(self):
-        table = []
-        for landmark, distance in self.distances.items():
-            table.append([landmark.replace("_", " "), distance])
-        output = tabulate(table,
-                          headers=["measurement", "value"],
-                          tablefmt="grid")
-        print(output)
-
-    def calculate_distance_betn_landmarks(self, front_results, landmarks=[]):
+    def calculate_distance_betn_landmarks(
+        self,
+        front_results,
+        measurement_name,
+    ):
         if not front_results.pose_landmarks:
             return
 
         landmarks = front_results.pose_landmarks.landmark
-        leg_landmarks = [
-            pose.PoseLandmark.LEFT_HIP,
-            pose.PoseLandmark.LEFT_KNEE,
-            pose.PoseLandmark.LEFT_ANKLE,
-        ]
-        hand_landmarks = [
-            pose.PoseLandmark.LEFT_SHOULDER,
-            pose.PoseLandmark.LEFT_ELBOW,
-            pose.PoseLandmark.LEFT_WRIST,
-        ]
-        self.landmarks_to_calculate = leg_landmarks + hand_landmarks
-        #            self.landmarks_to_calculate = [
-        #                pose.PoseLandmark.LEFT_SHOULDER,
-        #                pose.PoseLandmark.LEFT_ELBOW,
-        #                pose.PoseLandmark.LEFT_WRIST,
-        #            ]
+        landmark_names = self.measurements[measurement_name]
 
-        table = []
-        for idx, l in enumerate(self.landmarks_to_calculate):
-            if idx < len(self.landmarks_to_calculate) - 1:
-                _current = landmarks[l.value]
-                _nextl = self.landmarks_to_calculate[idx + 1]
-                _next = landmarks[_nextl.value]
-                pixel_distance = self.euclidean_distance(
-                    _current.x * self.resized_width,
-                    _current.y * self.resized_height,
-                    _next.x * self.resized_width,
-                    _next.y * self.resized_height)
-                real_distance = pixel_distance * self.pixel_to_metric_ratio()
-                table.append([l.name, _nextl.name, real_distance])
-
-        output = tabulate(
-            table,
-            headers=["Landmark 1", "Landmark 2", "Distance (cm)"],
-            tablefmt="grid")
-        print(output)
-
-
-#        for l in self.landmarks_to_calculate:
-#            real_distance = 0
-#            for idx, l in enumerate(self.landmarks_to_calculate):
-#                if idx < len(self.landmarks_to_calculate) - 1:
-#                    _current = landmarks[l.value]
-#                    _nextl = self.landmarks_to_calculate[idx + 1]
-#                    _next = landmarks[_nextl.value]
-#                    pixel_distance = self.euclidean_distance(
-#                        _current.x * self.resized_width,
-#                        _current.y * self.resized_height,
-#                        _next.x * self.resized_width,
-#                        _next.y * self.resized_height,
-#                    )
-#                    real_distance += pixel_distance * self.pixel_to_metric_ratio(
-#                    )
-#            print(real_distance)
-#            self.distances[l.name] = real_distance
-#
+        total_distance = 0
+        for idx in range(len(landmark_names) - 1):
+            _current = landmarks[landmark_names[idx]]
+            _next = landmarks[landmark_names[idx + 1]]
+            pixel_distance = self.euclidean_distance(
+                _current.x * self.resized_width,
+                _current.y * self.resized_height,
+                _next.x * self.resized_width,
+                _next.y * self.resized_height,
+            )
+            real_distance = pixel_distance * self.pixel_to_metric_ratio()
+            total_distance += real_distance
+        return total_distance
 
     def euclidean_distance(self, x1, y1, x2, y2):
-        distance = math.sqrt((x2 - x1)**2 + (y2 - y1)**2)
+        distance = math.sqrt((x2 - x1) ** 2 + (y2 - y1) ** 2)
         return distance
 
-    def destroy(self):
-        cv2.destroyAllWindows()
-
-    def display_images(self):
-        cv2.imshow("front_image_keypoints", self.front_image_keypoints)
-        cv2.imshow("side_image_keypoints", self.side_image_keypoints)
-        cv2.imshow("edges", self.edges)
-        cv2.waitKey(0)
 
     def get_center_top_point(self, side_results):
-        gray_image = cv2.cvtColor(self.side_image_keypoints,
-                                  cv2.COLOR_BGR2GRAY)
+        gray_image = cv2.cvtColor(
+            self.side_image_keypoints,
+            cv2.COLOR_BGR2GRAY,
+        )
         blurred_image = cv2.GaussianBlur(gray_image, (5, 5), 0)
-        roi = blurred_image[0:int(self.side_image_resized.shape[0] / 2), :]
-        self.edges = cv2.Canny(roi, 50, 150)
-        contours, _ = cv2.findContours(self.edges, cv2.RETR_EXTERNAL,
-                                       cv2.CHAIN_APPROX_SIMPLE)
+        roi = blurred_image[
+            0 : int(self.side_image_resized.shape[0] / 2),
+            :,
+        ]
+        edges = cv2.Canny(roi, 50, 150)
+        contours, _ = cv2.findContours(
+            edges,
+            cv2.RETR_EXTERNAL,
+            cv2.CHAIN_APPROX_SIMPLE,
+        )
         xt, yt = None, None
-        self.topmost_point = None
+        topmost_point = None
     
         if contours:
-            largest_contour = max(contours, key=cv2.contourArea)
-            self.topmost_point = tuple(
-                largest_contour[largest_contour[:, :, 1].argmin()][0])
-            xt, yt = self.topmost_point
-            self.circle(self.side_image_keypoints, xt, yt)
+            largest_contour = max(
+                contours,
+                key=cv2.contourArea,
+            )
+            topmost_point = tuple(largest_contour[largest_contour[:, :, 1].argmin()][0])
+            xt, yt = topmost_point
+    
+            cv2.circle(
+                self.side_image_keypoints,
+                (xt, yt),
+                2,
+                (255, 255, 0),
+                -1,
+            )
     
-            logging.warning("xt: %s", xt)
-            logging.warning("yt: %s", yt)
         xc, yc = None, None
         landmarks = side_results.pose_landmarks.landmark
     
         if side_results.pose_landmarks:
-            left_hip = landmarks[pose.PoseLandmark.LEFT_HIP.value]
-            right_hip = landmarks[pose.PoseLandmark.RIGHT_HIP.value]
+            left_hip = landmarks[LANDMARK_NAME_TO_INDEX["left_hip"]]
+            right_hip = landmarks[LANDMARK_NAME_TO_INDEX["right_hip"]]
             center_point = (
                 (left_hip.x + right_hip.x) / 2,
                 (left_hip.y + right_hip.y) / 2,
@@ -276,23 +331,26 @@ class Landmarker:
                 int(center_point[1] * self.side_image_resized.shape[0]),
             )
             xc, yc = center_point
-            logging.warning("xc: %s", xc)
-            logging.warning("yc: %s", yc)
-            self.circle(self.side_image_keypoints, xc, yc)
+            self.circle(
+                self.side_image_keypoints,
+                xc,
+                yc,
+            )
     
             self.pixel_distance = self.euclidean_distance(xc, yc, xt, yt)
-            logging.warning("top_center_pixel_distance: %s",
-                            self.pixel_distance)
+            logging.debug(
+                "top_center_pixel_distance: %s",
+                self.pixel_distance,
+            )
             self.pixel_height = self.pixel_distance * 2
-            logging.warning("pxl height: %s ", self.pixel_height)
-            self.distance = (self.euclidean_distance(xc, yc, xt, yt) *
-                             self.pixel_to_metric_ratio())
+            logging.debug(
+                "pixel height: %s ",
+                self.pixel_height,
+            )
+            self.distance = self.euclidean_distance(xc, yc, xt, yt) * self.pixel_to_metric_ratio()
+    
         return self.distance
 
-l = Landmarker()
-try:
-    l.run()
-except:
-    print("error")
-finally:
-    l.destroy()
+if __name__ == "__main__":
+    landmarker = Landmarker()
+    landmarker.run()

pyproject.toml

@@ -0,0 +1,3 @@
+[tool.black]
+line-length = 120
+

requirements.txt

@@ -0,0 +1,4 @@
+mediapipe==0.10.13
+tabulate==0.9.0
+opencv-python-headless==4.10.0.84
+pyyaml==6.0.1