diff --git a/modules/capturer.py b/modules/capturer.py index a87cf4c..952cb6d 100644 --- a/modules/capturer.py +++ b/modules/capturer.py @@ -2,19 +2,38 @@ from typing import Any import cv2 import modules.globals # Import the globals to check the color correction toggle +def list_available_cameras(max_tested: int = 10): + """ List all available camera indices. """ + available_cameras = [] + for i in range(max_tested): + cap = cv2.VideoCapture(i) + if cap.isOpened(): + available_cameras.append(i) + cap.release() + return available_cameras -def get_video_frame(video_path: str, frame_number: int = 0) -> Any: - capture = cv2.VideoCapture(video_path) +def get_video_frame(video_source: Any, frame_number: int = 0, is_camera: bool = False) -> Any: + """ + Capture a video frame from a camera or video file. + + :param video_source: The camera index or video file path. + :param frame_number: Frame number to retrieve (only applicable for video files). + :param is_camera: Flag to indicate if the source is a camera. + :return: The captured frame. + """ + capture = cv2.VideoCapture(video_source) # Set MJPEG format to ensure correct color space handling capture.set(cv2.CAP_PROP_FOURCC, cv2.VideoWriter_fourcc(*'MJPG')) - + # Only force RGB conversion if color correction is enabled if modules.globals.color_correction: capture.set(cv2.CAP_PROP_CONVERT_RGB, 1) - - frame_total = capture.get(cv2.CAP_PROP_FRAME_COUNT) - capture.set(cv2.CAP_PROP_POS_FRAMES, min(frame_total, frame_number - 1)) + + if not is_camera: + frame_total = capture.get(cv2.CAP_PROP_FRAME_COUNT) + capture.set(cv2.CAP_PROP_POS_FRAMES, min(frame_total, frame_number - 1)) + has_frame, frame = capture.read() if has_frame and modules.globals.color_correction: @@ -24,8 +43,8 @@ def get_video_frame(video_path: str, frame_number: int = 0) -> Any: capture.release() return frame if has_frame else None - def get_video_frame_total(video_path: str) -> int: + """ Get total frame count of a video file. """ capture = cv2.VideoCapture(video_path) video_frame_total = int(capture.get(cv2.CAP_PROP_FRAME_COUNT)) capture.release() diff --git a/modules/ui.py b/modules/ui.py index a8c6522..072500f 100644 --- a/modules/ui.py +++ b/modules/ui.py @@ -7,14 +7,12 @@ from PIL import Image, ImageOps import modules.globals import modules.metadata -from modules.face_analyser import get_one_face, get_unique_faces_from_target_image, get_unique_faces_from_target_video, add_blank_map, has_valid_map, simplify_maps +from modules.face_analyser import get_one_face from modules.capturer import get_video_frame, get_video_frame_total from modules.processors.frame.core import get_frame_processors_modules from modules.utilities import is_image, is_video, resolve_relative_path, has_image_extension ROOT = None -POPUP = None -POPUP_LIVE = None ROOT_HEIGHT = 700 ROOT_WIDTH = 600 @@ -24,22 +22,6 @@ PREVIEW_MAX_WIDTH = 1200 PREVIEW_DEFAULT_WIDTH = 960 PREVIEW_DEFAULT_HEIGHT = 540 -POPUP_WIDTH = 750 -POPUP_HEIGHT = 810 -POPUP_SCROLL_WIDTH = 740, -POPUP_SCROLL_HEIGHT = 700 - -POPUP_LIVE_WIDTH = 900 -POPUP_LIVE_HEIGHT = 820 -POPUP_LIVE_SCROLL_WIDTH = 890, -POPUP_LIVE_SCROLL_HEIGHT = 700 - -MAPPER_PREVIEW_MAX_HEIGHT = 100 -MAPPER_PREVIEW_MAX_WIDTH = 100 - -DEFAULT_BUTTON_WIDTH = 200 -DEFAULT_BUTTON_HEIGHT = 40 - RECENT_DIRECTORY_SOURCE = None RECENT_DIRECTORY_TARGET = None RECENT_DIRECTORY_OUTPUT = None @@ -49,11 +31,6 @@ preview_slider = None source_label = None target_label = None status_label = None -popup_status_label = None -popup_status_label_live = None -source_label_dict = {} -source_label_dict_live = {} -target_label_dict_live = {} img_ft, vid_ft = modules.globals.file_types @@ -65,6 +42,16 @@ def init(start: Callable[[], None], destroy: Callable[[], None]) -> ctk.CTk: PREVIEW = create_preview(ROOT) return ROOT + +def list_available_cameras(max_tested: int = 10): + """ List all available camera indices. """ + available_cameras = [] + for i in range(max_tested): + cap = cv2.VideoCapture(i) + if cap.isOpened(): + available_cameras.append(i) + cap.release() + return available_cameras def create_root(start: Callable[[], None], destroy: Callable[[], None]) -> ctk.CTk: @@ -90,11 +77,21 @@ def create_root(start: Callable[[], None], destroy: Callable[[], None]) -> ctk.C select_face_button.place(relx=0.1, rely=0.4, relwidth=0.3, relheight=0.1) swap_faces_button = ctk.CTkButton(root, text='↔', cursor='hand2', command=lambda: swap_faces_paths()) - swap_faces_button.place(relx=0.45, rely=0.4, relwidth=0.1, relheight=0.1) + swap_faces_button.place(relx=0.45, relwidth=0.1, relheight=0.1) select_target_button = ctk.CTkButton(root, text='Select a target', cursor='hand2', command=lambda: select_target_path()) select_target_button.place(relx=0.6, rely=0.4, relwidth=0.3, relheight=0.1) + # Create dropdown for camera selection + available_cameras = list_available_cameras() + if available_cameras: + camera_var = ctk.StringVar(value=str(available_cameras[0])) # Default to the first available camera + camera_dropdown = ctk.CTkOptionMenu(root, variable=camera_var, values=[str(i) for i in available_cameras]) + camera_dropdown.place(relx=0.1, rely=0.55, relwidth=0.5, relheight=0.05) + else: + camera_var = ctk.StringVar(value="No cameras found") + camera_dropdown = ctk.CTkLabel(root, text="No cameras found") + camera_dropdown.place(relx=0.1, rely=0.55, relwidth=0.5, relheight=0.05) keep_fps_value = ctk.BooleanVar(value=modules.globals.keep_fps) keep_fps_checkbox = ctk.CTkSwitch(root, text='Keep fps', variable=keep_fps_value, cursor='hand2', command=lambda: setattr(modules.globals, 'keep_fps', not modules.globals.keep_fps)) keep_fps_checkbox.place(relx=0.1, rely=0.6) @@ -124,12 +121,9 @@ def create_root(start: Callable[[], None], destroy: Callable[[], None]) -> ctk.C # nsfw_value = ctk.BooleanVar(value=modules.globals.nsfw_filter) # nsfw_switch = ctk.CTkSwitch(root, text='NSFW filter', variable=nsfw_value, cursor='hand2', command=lambda: setattr(modules.globals, 'nsfw_filter', nsfw_value.get())) # nsfw_switch.place(relx=0.6, rely=0.7) + - map_faces = ctk.BooleanVar(value=modules.globals.map_faces) - map_faces_switch = ctk.CTkSwitch(root, text='Map faces', variable=map_faces, cursor='hand2', command=lambda: setattr(modules.globals, 'map_faces', map_faces.get())) - map_faces_switch.place(relx=0.1, rely=0.75) - - start_button = ctk.CTkButton(root, text='Start', cursor='hand2', command=lambda: analyze_target(start, root)) + start_button = ctk.CTkButton(root, text='Start', cursor='hand2', command=lambda: select_output_path(start)) start_button.place(relx=0.15, rely=0.80, relwidth=0.2, relheight=0.05) stop_button = ctk.CTkButton(root, text='Destroy', cursor='hand2', command=lambda: destroy()) @@ -138,7 +132,7 @@ def create_root(start: Callable[[], None], destroy: Callable[[], None]) -> ctk.C preview_button = ctk.CTkButton(root, text='Preview', cursor='hand2', command=lambda: toggle_preview()) preview_button.place(relx=0.65, rely=0.80, relwidth=0.2, relheight=0.05) - live_button = ctk.CTkButton(root, text='Live', cursor='hand2', command=lambda: webcam_preview(root)) + live_button = ctk.CTkButton(root, text='Live', cursor='hand2', command=lambda: webcam_preview(int(camera_var.get()))) live_button.place(relx=0.40, rely=0.86, relwidth=0.2, relheight=0.05) status_label = ctk.CTkLabel(root, text=None, justify='center') @@ -151,108 +145,7 @@ def create_root(start: Callable[[], None], destroy: Callable[[], None]) -> ctk.C return root -def analyze_target(start: Callable[[], None], root: ctk.CTk): - if POPUP != None and POPUP.winfo_exists(): - update_status("Please complete pop-up or close it.") - return - if modules.globals.map_faces: - modules.globals.souce_target_map = [] - - if is_image(modules.globals.target_path): - update_status('Getting unique faces') - get_unique_faces_from_target_image() - elif is_video(modules.globals.target_path): - update_status('Getting unique faces') - get_unique_faces_from_target_video() - - if len(modules.globals.souce_target_map) > 0: - create_source_target_popup(start, root, modules.globals.souce_target_map) - else: - update_status("No faces found in target") - else: - select_output_path(start) - -def create_source_target_popup(start: Callable[[], None], root: ctk.CTk, map: list) -> None: - global POPUP, popup_status_label - - POPUP = ctk.CTkToplevel(root) - POPUP.title("Source x Target Mapper") - POPUP.geometry(f"{POPUP_WIDTH}x{POPUP_HEIGHT}") - POPUP.focus() - - def on_submit_click(start): - if has_valid_map(): - POPUP.destroy() - select_output_path(start) - else: - update_pop_status("Atleast 1 source with target is required!") - - scrollable_frame = ctk.CTkScrollableFrame(POPUP, width=POPUP_SCROLL_WIDTH, height=POPUP_SCROLL_HEIGHT) - scrollable_frame.grid(row=0, column=0, padx=0, pady=0, sticky='nsew') - - def on_button_click(map, button_num): - map = update_popup_source(scrollable_frame, map, button_num) - - for item in map: - id = item['id'] - - button = ctk.CTkButton(scrollable_frame, text="Select source image", command=lambda id=id: on_button_click(map, id), width=DEFAULT_BUTTON_WIDTH, height=DEFAULT_BUTTON_HEIGHT) - button.grid(row=id, column=0, padx=50, pady=10) - - x_label = ctk.CTkLabel(scrollable_frame, text=f"X", width=MAPPER_PREVIEW_MAX_WIDTH, height=MAPPER_PREVIEW_MAX_HEIGHT) - x_label.grid(row=id, column=2, padx=10, pady=10) - - image = Image.fromarray(cv2.cvtColor(item['target']['cv2'], cv2.COLOR_BGR2RGB)) - image = image.resize((MAPPER_PREVIEW_MAX_WIDTH, MAPPER_PREVIEW_MAX_HEIGHT), Image.LANCZOS) - tk_image = ctk.CTkImage(image, size=image.size) - - target_image = ctk.CTkLabel(scrollable_frame, text=f"T-{id}", width=MAPPER_PREVIEW_MAX_WIDTH, height=MAPPER_PREVIEW_MAX_HEIGHT) - target_image.grid(row=id, column=3, padx=10, pady=10) - target_image.configure(image=tk_image) - - popup_status_label = ctk.CTkLabel(POPUP, text=None, justify='center') - popup_status_label.grid(row=1, column=0, pady=15) - - close_button = ctk.CTkButton(POPUP, text="Submit", command=lambda: on_submit_click(start)) - close_button.grid(row=2, column=0, pady=10) - - -def update_popup_source(scrollable_frame: ctk.CTkScrollableFrame, map: list, button_num: int) -> list: - global source_label_dict - - source_path = ctk.filedialog.askopenfilename(title='select an source image', initialdir=RECENT_DIRECTORY_SOURCE, filetypes=[img_ft]) - - if "source" in map[button_num]: - map[button_num].pop("source") - source_label_dict[button_num].destroy() - del source_label_dict[button_num] - - if source_path == "": - return map - else: - cv2_img = cv2.imread(source_path) - face = get_one_face(cv2_img) - - if face: - x_min, y_min, x_max, y_max = face['bbox'] - - map[button_num]['source'] = { - 'cv2' : cv2_img[int(y_min):int(y_max), int(x_min):int(x_max)], - 'face' : face - } - - image = Image.fromarray(cv2.cvtColor(map[button_num]['source']['cv2'], cv2.COLOR_BGR2RGB)) - image = image.resize((MAPPER_PREVIEW_MAX_WIDTH, MAPPER_PREVIEW_MAX_HEIGHT), Image.LANCZOS) - tk_image = ctk.CTkImage(image, size=image.size) - - source_image = ctk.CTkLabel(scrollable_frame, text=f"S-{button_num}", width=MAPPER_PREVIEW_MAX_WIDTH, height=MAPPER_PREVIEW_MAX_HEIGHT) - source_image.grid(row=button_num, column=1, padx=10, pady=10) - source_image.configure(image=tk_image) - source_label_dict[button_num] = source_image - else: - update_pop_status("Face could not be detected in last upload!") - return map def create_preview(parent: ctk.CTkToplevel) -> ctk.CTkToplevel: @@ -277,11 +170,6 @@ def update_status(text: str) -> None: status_label.configure(text=text) ROOT.update() -def update_pop_status(text: str) -> None: - popup_status_label.configure(text=text) - -def update_pop_live_status(text: str) -> None: - popup_status_label_live.configure(text=text) def update_tumbler(var: str, value: bool) -> None: modules.globals.fp_ui[var] = value @@ -450,20 +338,14 @@ def update_preview(frame_number: int = 0) -> None: update_status('Processing succeed!') PREVIEW.deiconify() -def webcam_preview(root: ctk.CTk): - if not modules.globals.map_faces: - if modules.globals.source_path is None: - # No image selected - return - create_webcam_preview() - else: - modules.globals.souce_target_map = [] - create_source_target_popup_for_webcam(root, modules.globals.souce_target_map) +def webcam_preview(camera_index=0): + if modules.globals.source_path is None: + # No image selected + return -def create_webcam_preview(): global preview_label, PREVIEW - camera = cv2.VideoCapture(0) # Use index for the webcam (adjust the index accordingly if necessary) + camera = cv2.VideoCapture(camera_index) # Use the selected camera index camera.set(cv2.CAP_PROP_FRAME_WIDTH, PREVIEW_DEFAULT_WIDTH) # Set the width of the resolution camera.set(cv2.CAP_PROP_FRAME_HEIGHT, PREVIEW_DEFAULT_HEIGHT) # Set the height of the resolution camera.set(cv2.CAP_PROP_FPS, 60) # Set the frame rate of the webcam @@ -481,26 +363,20 @@ def create_webcam_preview(): if not ret: break - temp_frame = frame.copy() #Create a copy of the frame + # Select and save face image only once + if source_image is None and modules.globals.source_path: + source_image = get_one_face(cv2.imread(modules.globals.source_path)) + + temp_frame = frame.copy() # Create a copy of the frame if modules.globals.live_mirror: - temp_frame = cv2.flip(temp_frame, 1) # horizontal flipping + temp_frame = cv2.flip(temp_frame, 1) # Horizontal flipping if modules.globals.live_resizable: temp_frame = fit_image_to_size(temp_frame, PREVIEW.winfo_width(), PREVIEW.winfo_height()) - if not modules.globals.map_faces: - # Select and save face image only once - if source_image is None and modules.globals.source_path: - source_image = get_one_face(cv2.imread(modules.globals.source_path)) - - for frame_processor in frame_processors: - temp_frame = frame_processor.process_frame(source_image, temp_frame) - else: - modules.globals.target_path = None - - for frame_processor in frame_processors: - temp_frame = frame_processor.process_frame_v2(temp_frame) + for frame_processor in frame_processors: + temp_frame = frame_processor.process_frame(source_image, temp_frame) image = cv2.cvtColor(temp_frame, cv2.COLOR_BGR2RGB) # Convert the image to RGB format to display it with Tkinter image = Image.fromarray(image) @@ -514,151 +390,3 @@ def create_webcam_preview(): camera.release() PREVIEW.withdraw() # Close preview window when loop is finished - - -def create_source_target_popup_for_webcam(root: ctk.CTk, map: list) -> None: - global POPUP_LIVE, popup_status_label_live - - POPUP_LIVE = ctk.CTkToplevel(root) - POPUP_LIVE.title("Source x Target Mapper") - POPUP_LIVE.geometry(f"{POPUP_LIVE_WIDTH}x{POPUP_LIVE_HEIGHT}") - POPUP_LIVE.focus() - - def on_submit_click(): - if has_valid_map(): - POPUP_LIVE.destroy() - simplify_maps() - create_webcam_preview() - else: - update_pop_live_status("Atleast 1 source with target is required!") - - def on_add_click(): - add_blank_map() - refresh_data(map) - update_pop_live_status("Please provide mapping!") - - popup_status_label_live = ctk.CTkLabel(POPUP_LIVE, text=None, justify='center') - popup_status_label_live.grid(row=1, column=0, pady=15) - - add_button = ctk.CTkButton(POPUP_LIVE, text="Add", command=lambda: on_add_click()) - add_button.place(relx=0.2, rely=0.92, relwidth=0.2, relheight=0.05) - - close_button = ctk.CTkButton(POPUP_LIVE, text="Submit", command=lambda: on_submit_click()) - close_button.place(relx=0.6, rely=0.92, relwidth=0.2, relheight=0.05) - - -def refresh_data(map: list): - global POPUP_LIVE - - scrollable_frame = ctk.CTkScrollableFrame(POPUP_LIVE, width=POPUP_LIVE_SCROLL_WIDTH, height=POPUP_LIVE_SCROLL_HEIGHT) - scrollable_frame.grid(row=0, column=0, padx=0, pady=0, sticky='nsew') - - def on_sbutton_click(map, button_num): - map = update_webcam_source(scrollable_frame, map, button_num) - - def on_tbutton_click(map, button_num): - map = update_webcam_target(scrollable_frame, map, button_num) - - for item in map: - id = item['id'] - - button = ctk.CTkButton(scrollable_frame, text="Select source image", command=lambda id=id: on_sbutton_click(map, id), width=DEFAULT_BUTTON_WIDTH, height=DEFAULT_BUTTON_HEIGHT) - button.grid(row=id, column=0, padx=30, pady=10) - - x_label = ctk.CTkLabel(scrollable_frame, text=f"X", width=MAPPER_PREVIEW_MAX_WIDTH, height=MAPPER_PREVIEW_MAX_HEIGHT) - x_label.grid(row=id, column=2, padx=10, pady=10) - - button = ctk.CTkButton(scrollable_frame, text="Select target image", command=lambda id=id: on_tbutton_click(map, id), width=DEFAULT_BUTTON_WIDTH, height=DEFAULT_BUTTON_HEIGHT) - button.grid(row=id, column=3, padx=20, pady=10) - - if "source" in item: - image = Image.fromarray(cv2.cvtColor(item['source']['cv2'], cv2.COLOR_BGR2RGB)) - image = image.resize((MAPPER_PREVIEW_MAX_WIDTH, MAPPER_PREVIEW_MAX_HEIGHT), Image.LANCZOS) - tk_image = ctk.CTkImage(image, size=image.size) - - source_image = ctk.CTkLabel(scrollable_frame, text=f"S-{id}", width=MAPPER_PREVIEW_MAX_WIDTH, height=MAPPER_PREVIEW_MAX_HEIGHT) - source_image.grid(row=id, column=1, padx=10, pady=10) - source_image.configure(image=tk_image) - - if "target" in item: - image = Image.fromarray(cv2.cvtColor(item['target']['cv2'], cv2.COLOR_BGR2RGB)) - image = image.resize((MAPPER_PREVIEW_MAX_WIDTH, MAPPER_PREVIEW_MAX_HEIGHT), Image.LANCZOS) - tk_image = ctk.CTkImage(image, size=image.size) - - target_image = ctk.CTkLabel(scrollable_frame, text=f"T-{id}", width=MAPPER_PREVIEW_MAX_WIDTH, height=MAPPER_PREVIEW_MAX_HEIGHT) - target_image.grid(row=id, column=4, padx=20, pady=10) - target_image.configure(image=tk_image) - - -def update_webcam_source(scrollable_frame: ctk.CTkScrollableFrame, map: list, button_num: int) -> list: - global source_label_dict_live - - source_path = ctk.filedialog.askopenfilename(title='select an source image', initialdir=RECENT_DIRECTORY_SOURCE, filetypes=[img_ft]) - - if "source" in map[button_num]: - map[button_num].pop("source") - source_label_dict_live[button_num].destroy() - del source_label_dict_live[button_num] - - if source_path == "": - return map - else: - cv2_img = cv2.imread(source_path) - face = get_one_face(cv2_img) - - if face: - x_min, y_min, x_max, y_max = face['bbox'] - - map[button_num]['source'] = { - 'cv2' : cv2_img[int(y_min):int(y_max), int(x_min):int(x_max)], - 'face' : face - } - - image = Image.fromarray(cv2.cvtColor(map[button_num]['source']['cv2'], cv2.COLOR_BGR2RGB)) - image = image.resize((MAPPER_PREVIEW_MAX_WIDTH, MAPPER_PREVIEW_MAX_HEIGHT), Image.LANCZOS) - tk_image = ctk.CTkImage(image, size=image.size) - - source_image = ctk.CTkLabel(scrollable_frame, text=f"S-{button_num}", width=MAPPER_PREVIEW_MAX_WIDTH, height=MAPPER_PREVIEW_MAX_HEIGHT) - source_image.grid(row=button_num, column=1, padx=10, pady=10) - source_image.configure(image=tk_image) - source_label_dict_live[button_num] = source_image - else: - update_pop_live_status("Face could not be detected in last upload!") - return map - -def update_webcam_target(scrollable_frame: ctk.CTkScrollableFrame, map: list, button_num: int) -> list: - global target_label_dict_live - - target_path = ctk.filedialog.askopenfilename(title='select an target image', initialdir=RECENT_DIRECTORY_SOURCE, filetypes=[img_ft]) - - if "target" in map[button_num]: - map[button_num].pop("target") - target_label_dict_live[button_num].destroy() - del target_label_dict_live[button_num] - - if target_path == "": - return map - else: - cv2_img = cv2.imread(target_path) - face = get_one_face(cv2_img) - - if face: - x_min, y_min, x_max, y_max = face['bbox'] - - map[button_num]['target'] = { - 'cv2' : cv2_img[int(y_min):int(y_max), int(x_min):int(x_max)], - 'face' : face - } - - image = Image.fromarray(cv2.cvtColor(map[button_num]['target']['cv2'], cv2.COLOR_BGR2RGB)) - image = image.resize((MAPPER_PREVIEW_MAX_WIDTH, MAPPER_PREVIEW_MAX_HEIGHT), Image.LANCZOS) - tk_image = ctk.CTkImage(image, size=image.size) - - target_image = ctk.CTkLabel(scrollable_frame, text=f"T-{button_num}", width=MAPPER_PREVIEW_MAX_WIDTH, height=MAPPER_PREVIEW_MAX_HEIGHT) - target_image.grid(row=button_num, column=4, padx=20, pady=10) - target_image.configure(image=tk_image) - target_label_dict_live[button_num] = target_image - else: - update_pop_live_status("Face could not be detected in last upload!") - return map -