Update TheDistanceAssessor.py

TheDistanceAssessor.py

@@ -836,7 +836,10 @@ def draw_classification(classification, id_map):
 def get_result(classification, id_map, names, borders, image, regions):
         image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
         image = cv2.resize(image, (id_map.shape[1], id_map.shape[0]), interpolation = cv2.INTER_LINEAR)
-        fig = plt.figure(figsize=(16, 9), dpi=100)
+        
+        ratio = image.shape[0] / image.shape[1]
+        
+        fig = plt.figure(figsize=(16, 16*ratio), dpi=100)
         plt.imshow(image, cmap='gray')
         
         if classification:
@@ -863,8 +866,8 @@ def get_result(classification, id_map, names, borders, image, regions):
                         for line in side:
                                 line = np.array(line)
                                 plt.plot(line[:,1], line[:,0] ,'-', color='lightgrey', marker=None, linewidth=0.5)
-                                plt.ylim(0, 1080)
-                                plt.xlim(0, 1920)
+                                #plt.ylim(0, 1080)
+                                #plt.xlim(0, 1920)
                                 plt.gca().invert_yaxis()
 
         colors = ['yellow','orange','red']
@@ -874,10 +877,11 @@ def get_result(classification, id_map, names, borders, image, regions):
                         side = np.array(side)
                         if side.size > 0:
                                 plt.plot(side[:,0],side[:,1] ,'-', color=colors[i], marker=None, linewidth=0.6) #color=colors[i]
-                                plt.ylim(0, 1080)
-                                plt.xlim(0, 1920)
+                                #plt.ylim(0, 1080)
+                                #plt.xlim(0, 1920)
                                 plt.gca().invert_yaxis()
-                
+        
+        plt.xlim(left=0)  # Ensure only positive X values are displayed
         plt.tight_layout()
         canvas = FigureCanvas(fig)
         canvas.draw()
@@ -904,7 +908,7 @@ def run(input_image, model_seg, model_det, image_size, target_distances, num_ys
         classification = classify_detections(boxes_moving, boxes_stationary, borders, image.shape, output_dims=segmentation_mask.shape)
 
         output_image = get_result(classification, id_map, model.names, borders, image, regions)
-        #cropped_image = output_image[22:output_image.shape[0] - 40, 74:output_image.shape[1] - 33]
+        cropped_image = output_image[22:output_image.shape[0] - 40, 74:output_image.shape[1] - 33]
         return output_image
 
 if __name__ == "__main__":