def svg_overlay(faces, frame_size, joy_score): width, height = frame_size doc = svg.Svg(width=width, height=height) for face in faces: x, y, w, h = face.bounding_box doc.add( svg.Rect(x=int(x), y=int(y), width=int(w), height=int(h), rx=10, ry=10, fill_opacity=0.3 * face.face_score, style='fill:red;stroke:white;stroke-width:4px')) doc.add( svg.Text('Joy: %.2f' % face.joy_score, x=x, y=y - 10, fill='red', font_size=30)) doc.add( svg.Text('Faces: %d Avg. joy: %.2f' % (len(faces), joy_score), x=10, y=50, fill='red', font_size=40)) return str(doc)
def plot_svg_chart(svg_doc, location, data): x, y, x2, y2 = LOCATIONS[location] plotted_data = sorted(list(data[location].keys()))[-20:] for pos, time in enumerate(plotted_data): start_x = (x + 8 * pos) * SVG_SCALE_FACTOR width = 4 * SVG_SCALE_FACTOR start_y = (y - 20 * data[location][time]) height = (y - start_y) * SVG_SCALE_FACTOR start_y = start_y * SVG_SCALE_FACTOR color = 'red' if data[location][time] == 2 else 'green' svg_doc.add( svg.Rect(x=int(start_x), y=int(start_y), width=int(width), height=int(height), fill_opacity=0.3, style='fill:' + color + ';stroke:' + color + ';stroke-width:4px'))
def main(): parser = argparse.ArgumentParser() parser.add_argument('--dog_park_model_path', help='Path to the model file for the dog park.') parser.add_argument('--vb1_model_path', help='Path to the model file for volley ball court 1.') parser.add_argument('--vb2_model_path', help='Path to the model file for volley ball court 1.') parser.add_argument( '--label_path', required=True, help='Path to label file that corresponds to the model.') parser.add_argument('--input_mean', type=float, default=128.0, help='Input mean.') parser.add_argument('--input_std', type=float, default=128.0, help='Input std.') parser.add_argument('--input_depth', type=int, default=3, help='Input depth.') parser.add_argument('--enable_streaming', default=False, action='store_true', help='Enable streaming server') parser.add_argument('--streaming_bitrate', type=int, default=1000000, help='Streaming server video bitrate (kbps)') parser.add_argument('--mdns_name', default='', help='Streaming server mDNS name') parser.add_argument( '--preview', action='store_true', default=False, help= 'Enables camera preview in addition to printing result to terminal.') parser.add_argument( '--time_interval', type=int, default=10, help='Time interval at which to store data in seconds.') parser.add_argument( '--gather_data', action='store_true', default=False, help='Also save images according to the assigned category.') parser.add_argument( '--timelapse', action='store_true', default=False, help='Also save some timelapses of the entire scene, every 120 seconds.' ) parser.add_argument('--image_folder', default='/home/pi/Pictures/Data', help='Folder to save captured images') args = parser.parse_args() labels = read_labels(args.label_path) # At least one model needs to be passed in. assert args.dog_park_model_path or args.vb1_model_path or args.vb2_model_path # Check that the folder exists if args.gather_data: expected_subfolders = ['dog_park', 'court_one', 'court_two'] subfolders = os.listdir(args.image_folder) for folder in expected_subfolders: assert folder in subfolders with ExitStack() as stack: dog_park = { 'location_name': 'dog_park', 'path': args.dog_park_model_path, } if args.dog_park_model_path else None vb1 = { 'location_name': 'court_one', 'path': args.vb1_model_path, } if args.vb1_model_path else None vb2 = { 'location_name': 'court_two', 'path': args.vb2_model_path, } if args.vb2_model_path else None # Get the list of models, filter to only the ones that were passed in. models = [dog_park, vb1, vb2] models = list(filter(lambda model: model, models)) # Initialize models and add them to the context for model in models: print('Initializing {model_name}...'.format( model_name=model["location_name"])) descriptor = inference.ModelDescriptor( name='mobilenet_based_classifier', input_shape=(1, 160, 160, args.input_depth), input_normalizer=(args.input_mean, args.input_std), compute_graph=utils.load_compute_graph(model['path'])) model['descriptor'] = descriptor if dog_park: dog_park['image_inference'] = stack.enter_context( inference.ImageInference(dog_park['descriptor'])) if vb1: vb1['image_inference'] = stack.enter_context( inference.ImageInference(vb1['descriptor'])) if vb2: vb2['image_inference'] = stack.enter_context( inference.ImageInference(vb2['descriptor'])) camera = stack.enter_context( PiCamera(sensor_mode=4, resolution=(820, 616), framerate=30)) server = None if args.enable_streaming: server = stack.enter_context( StreamingServer(camera, bitrate=args.streaming_bitrate, mdns_name=args.mdns_name)) if args.preview: # Draw bounding boxes around locations # Load the arbitrarily sized image img = Image.new('RGB', (820, 616)) draw = ImageDraw.Draw(img) for location in LOCATIONS.values(): x1, y1, x2, y2 = location draw_rectangle(draw, x1, y1, x2, y2, 3, outline='white') # Create an image padded to the required size with # mode 'RGB' pad = Image.new('RGB', ( ((img.size[0] + 31) // 32) * 32, ((img.size[1] + 15) // 16) * 16, )) # Paste the original image into the padded one pad.paste(img, (0, 0)) # Add the overlay with the padded image as the source, # but the original image's dimensions camera.add_overlay(pad.tobytes(), alpha=64, layer=3, size=img.size) camera.start_preview() data_filename = _make_filename(args.image_folder, 'data', None, 'json') data_generator = commit_data_to_long_term(args.time_interval, data_filename) data_generator.send(None) # Capture one picture of entire scene each time it's started again. time.sleep(2) date = time.strftime('%Y-%m-%d') scene_filename = _make_filename(args.image_folder, date, None) camera.capture(scene_filename) # Draw bounding box on image showing the crop locations with Image.open(scene_filename) as scene: draw = ImageDraw.Draw(scene) for location in LOCATIONS.values(): x1, y1, x2, y2 = location draw_rectangle(draw, x1, y1, x2, y2, 3, outline='white') scene.save(scene_filename) # Constantly get cropped images for cropped_images in get_cropped_images(camera, args.timelapse): svg_doc = None if args.enable_streaming: width = 820 * SVG_SCALE_FACTOR height = 616 * SVG_SCALE_FACTOR svg_doc = svg.Svg(width=width, height=height) for location in LOCATIONS.values(): x, y, x2, y2 = location w = (x2 - x) * SVG_SCALE_FACTOR h = (y2 - y) * SVG_SCALE_FACTOR x = x * SVG_SCALE_FACTOR y = y * SVG_SCALE_FACTOR svg_doc.add( svg.Rect( x=int(x), y=int(y), width=int(w), height=int(h), rx=10, ry=10, fill_opacity=0.3, style='fill:none;stroke:white;stroke-width:4px')) # For each inference model, crop and process a different thing. for model in models: location_name = model['location_name'] image_inference = model['image_inference'] cropped_image = cropped_images[location_name] # TODO: (Image Comparison) If False,return no activity. if cropped_image: # then run image_inference on them. result = image_inference.run(cropped_image) processed_result = process(result, labels, 'final_result') data_generator.send( (location_name, processed_result, svg_doc)) message = get_message(processed_result) # Print the message # print('\n') # print('{location_name}:'.format(location_name=location_name)) # print(message) else: # Fake processed_result processed_result = [('inactive', 1.00), ('active', 0.00)] data_generator.send( (location_name, processed_result, svg_doc)) label = processed_result[0][0] timestamp = time.strftime('%Y-%m-%d_%H.%M.%S') # print(timestamp) # print('\n') if args.gather_data and cropped_image: # Gather 1% data on 'no activity' since it's biased against that. # Gather 0.1% of all images. if ( # (label == 'no activity' and random.random() > 0.99) or # (random.random() > 0.999) # (location_name != 'dog_park' and random.random() > 0.99) or (random.random() > 0.9)): subdir = '{location_name}/{label}'.format( location_name=location_name, label=label) filename = _make_filename(args.image_folder, timestamp, subdir) cropped_image.save(filename) # if svg_doc: # ## Plot points out # ## 160 x 80 grid # ## 16px width # ## 20, 40, 60 for 0, 1, 2 # lines = message.split('\n') # y_correction = len(lines) * 20 # for line in lines: # svg_doc.add(svg.Text(line, # x=(LOCATIONS[location_name][0]) * SVG_SCALE_FACTOR, # y=(LOCATIONS[location_name][1] - y_correction) * SVG_SCALE_FACTOR, # fill='white', font_size=20)) # y_correction = y_correction - 20 # TODO: Figure out how to annotate at specific locations. # if args.preview: # camera.annotate_foreground = Color('black') # camera.annotate_background = Color('white') # # PiCamera text annotation only supports ascii. # camera.annotate_text = '\n %s' % message.encode( # 'ascii', 'backslashreplace').decode('ascii') if server: server.send_overlay(str(svg_doc)) if args.preview: camera.stop_preview()