o W h@sddlZddlmZddlZddlZddlmZddlm Z m Z m Z m Z ddl mZmZddlmZGdddZGd d d eZGd d d ZdS) N) defaultdict)YOLO) ASSETS_URLDEFAULT_CFG_DICTDEFAULT_SOL_DICTLOGGER) check_imshowcheck_requirements) Annotatorc@sTeZdZdZdddZdddZdd Zd d Zd d ZddZ ddZ ddZ dS) BaseSolutiona A base class for managing Ultralytics Solutions. This class provides core functionality for various Ultralytics Solutions, including model loading, object tracking, and region initialization. Attributes: LineString (shapely.geometry.LineString): Class for creating line string geometries. Polygon (shapely.geometry.Polygon): Class for creating polygon geometries. Point (shapely.geometry.Point): Class for creating point geometries. CFG (dict): Configuration dictionary loaded from a YAML file and updated with kwargs. region (List[Tuple[int, int]]): List of coordinate tuples defining a region of interest. line_width (int): Width of lines used in visualizations. model (ultralytics.YOLO): Loaded YOLO model instance. names (Dict[int, str]): Dictionary mapping class indices to class names. env_check (bool): Flag indicating whether the environment supports image display. track_history (collections.defaultdict): Dictionary to store tracking history for each object. Methods: extract_tracks: Apply object tracking and extract tracks from an input image. store_tracking_history: Store object tracking history for a given track ID and bounding box. initialize_region: Initialize the counting region and line segment based on configuration. display_output: Display the results of processing, including showing frames or saving results. Examples: >>> solution = BaseSolution(model="yolo11n.pt", region=[(0, 0), (100, 0), (100, 100), (0, 100)]) >>> solution.initialize_region() >>> image = cv2.imread("image.jpg") >>> solution.extract_tracks(image) >>> solution.display_output(image) Fc  stdddlm}m}m}ddlm}|_|_|_|_d_d_d_ g_ g_ g_ d_ d_d_t_t|t|itt_jdtjd_jdd vrjjdnd _jd duryd jd <tjd _jj_jd _jd_jd_fdddD_|rֈjddurdjd vrdnd}jdt d|ddl!m"}|t d||jd<t#dd_$t%t&_'dS)a Initializes the BaseSolution class with configuration settings and the YOLO model. Args: is_cli (bool): Enables CLI mode if set to True. **kwargs (Any): Additional configuration parameters that override defaults. zshapely>=2.0.0,<2.1.0r) LineStringPointPolygon)prepNuUltralytics Solutions: ✅ region line_width)Nrmodelz yolo11n.ptclasses show_conf show_labelscsi|]}|j|qS)CFG).0kselfrS/var/www/vscode/kcb/lib/python3.10/site-packages/ultralytics/solutions/solutions.py ^s z)BaseSolution.__init__..)iouconfdevicemax_dethalftrackerr!verbosesourcez-posezsolutions_ci_demo.mp4zsolution_ci_pose_demo.mp4z*source not provided. using default source /) safe_downloadT)warn)(r shapely.geometryr r rshapely.preparedr annotatortracks track_databoxesclss track_ids track_linemasksr_srrupdaterrinforrrrnamesrrrtrack_add_argswarningrultralytics.utils.downloadsr(r env_checkrlist track_history) ris_clikwargsr r rrd_sr(rrr__init__0sR             zBaseSolution.__init__NcCsD|durdn|d|j|}|jr |jr|d|dS|SdS)a Generates a formatted label for a bounding box. This method constructs a label string for a bounding box using the class index and confidence score. Optionally includes the track ID if provided. The label format adapts based on the display settings defined in `self.show_conf` and `self.show_labels`. Args: cls (int): The class index of the detected object. conf (float): The confidence score of the detection. track_id (int, optional): The unique identifier for the tracked object. Defaults to None. Returns: (str or None): The formatted label string if `self.show_labels` is True; otherwise, None. N .2f)r7rr)rclsr track_idnamerrradjust_box_labelns $zBaseSolution.adjust_box_labelcCs|jjd|d|jd|j|_|jdjp|jdj|_t|jddr3|jdj dur3|jdj nd|_ |jre|jj dure|jj |_|jj |_|jj  |_|jj |_dS|jdggggf\|_|_|_|_dS)aF Applies object tracking and extracts tracks from an input image or frame. Args: im0 (np.ndarray): The input image or frame. Examples: >>> solution = BaseSolution() >>> frame = cv2.imread("path/to/image.jpg") >>> solution.extract_tracks(frame) T)r&persistrrr3Nzno tracks found!r)rtrackrr8r-obbr/r.hasattrr3idxyxycpurEtolistr0intr1r confsrr9)rim0rrrextract_trackss .  zBaseSolution.extract_trackscCs^|j||_|j|d|dd|d|ddft|jdkr-|jddSdS)aS Stores the tracking history of an object. This method updates the tracking history for a given object by appending the center point of its bounding box to the track line. It maintains a maximum of 30 points in the tracking history. Args: track_id (int): The unique identifier for the tracked object. box (List[float]): The bounding box coordinates of the object in the format [x1, y1, x2, y2]. Examples: >>> solution = BaseSolution() >>> solution.store_tracking_history(1, [100, 200, 300, 400]) rrN)r=r2appendlenpop)rrFboxrrrstore_tracking_historys 0z#BaseSolution.store_tracking_historycCsF|jdur gd|_t|jdkr||j|_dS||j|_dS)zPInitialize the counting region and line segment based on configuration settings.N)))8r^)r_h)r]r`rV)rrYrr r4rrrrinitialize_regions   zBaseSolution.initialize_regioncCsL|jdr |jr"td|tdd@tdkr$tdSdSdSdS)aX Display the results of the processing, which could involve showing frames, printing counts, or saving results. This method is responsible for visualizing the output of the object detection and tracking process. It displays the processed frame with annotations, and allows for user interaction to close the display. Args: plot_im (numpy.ndarray): The image or frame that has been processed and annotated. Examples: >>> solution = BaseSolution() >>> frame = cv2.imread("path/to/image.jpg") >>> solution.display_output(frame) Notes: - This method will only display output if the 'show' configuration is set to True and the environment supports image display. - The display can be closed by pressing the 'q' key. showzUltralytics SolutionsrUqN)rgetr;cv2imshowwaitKeyorddestroyAllWindows)rplot_imrrrdisplay_outputs zBaseSolution.display_outputcOsdS)z?Process method should be implemented by each Solution subclass.Nr)rargsr?rrrprocessszBaseSolution.processcOs.|j|i|}|jdrtd||S)zEAllow instances to be called like a function with flexible arguments.r%u🚀 Results: )rnrrr6)rrmr?resultrrr__call__s zBaseSolution.__call__)F)N) __name__ __module__ __qualname____doc__rArHrTr\rarlrnrprrrrr s > r cseZdZdZd/fdd Zd0d d Zd1ddZddZeddZ d2ddZ d3ddZ d3ddZ d4ddZ d d!Zd5d$d%Zd6d'd(Zd7d+d,Zd8d-d.ZZS)9SolutionAnnotatoraV A specialized annotator class for visualizing and analyzing computer vision tasks. This class extends the base Annotator class, providing additional methods for drawing regions, centroids, tracking trails, and visual annotations for Ultralytics Solutions: https://docs.ultralytics.com/solutions/. and parking management. Attributes: im (np.ndarray): The image being annotated. line_width (int): Thickness of lines used in annotations. font_size (int): Size of the font used for text annotations. font (str): Path to the font file used for text rendering. pil (bool): Whether to use PIL for text rendering. example (str): An example attribute for demonstration purposes. Methods: draw_region: Draws a region using specified points, colors, and thickness. queue_counts_display: Displays queue counts in the specified region. display_analytics: Displays overall statistics for parking lot management. estimate_pose_angle: Calculates the angle between three points in an object pose. draw_specific_points: Draws specific keypoints on the image. plot_workout_information: Draws a labeled text box on the image. plot_angle_and_count_and_stage: Visualizes angle, step count, and stage for workout monitoring. plot_distance_and_line: Displays the distance between centroids and connects them with a line. display_objects_labels: Annotates bounding boxes with object class labels. sweep_annotator: Visualizes a vertical sweep line and optional label. visioneye: Maps and connects object centroids to a visual "eye" point. circle_label: Draws a circular label within a bounding box. text_label: Draws a rectangular label within a bounding box. Examples: >>> annotator = SolutionAnnotator(image) >>> annotator.draw_region([(0, 0), (100, 100)], color=(0, 255, 0), thickness=5) >>> annotator.display_analytics( ... image, text={"Available Spots": 5}, txt_color=(0, 0, 0), bg_color=(255, 255, 255), margin=10 ... ) N Arial.ttfFabccst||||||dS)a Initializes the SolutionAnnotator class with an image for annotation. Args: im (np.ndarray): The image to be annotated. line_width (int, optional): Line thickness for drawing on the image. font_size (int, optional): Font size for text annotations. font (str, optional): Path to the font file. pil (bool, optional): Indicates whether to use PIL for rendering text. example (str, optional): An example parameter for demonstration purposes. N)superrA)rimr font_sizefontpilexample __class__rrrAs zSolutionAnnotator.__init__rrcrcCsVtj|jtj|tjdgd||d|D]}t|j|d|df|d|dqdS) a8 Draw a region or line on the image. Args: reg_pts (List[Tuple[int, int]]): Region points (for line 2 points, for region 4+ points). color (Tuple[int, int, int]): RGB color value for the region. thickness (int): Line thickness for drawing the region. )dtypeT)isClosedcolor thicknessrrUrN)rf polylinesrynparrayint32circle)rreg_ptsrrpointrrr draw_regions$ &zSolutionAnnotator.draw_regionrcrcrcrrrc Csdd|D}dd|D}t|t|}t|t|}tj|d|j|jdd} | d} | d} | d} | d} || d|| df}|| d|| df}t|j|||d || d}|| d}tj|j|||fd|j||jtj d d S) a Displays queue counts on an image centered at the points with customizable font size and colors. Args: label (str): Queue counts label. points (List[Tuple[int, int]]): Region points for center point calculation to display text. region_color (Tuple[int, int, int]): RGB queue region color. txt_color (Tuple[int, int, int]): RGB text display color. cSg|]}|dqS)rrrrrrr -z:SolutionAnnotator.queue_counts_display..cSr)rUrrrrrr.rr fontScalerrUr]rr)rrrlineTypeN) sumrYrf getTextSizesftf rectangleryputTextLINE_AA)rlabelpoints region_color txt_colorx_valuesy_valuescenter_xcenter_y text_size text_width text_height rect_width rect_height rect_top_leftrect_bottom_righttext_xtext_yrrrqueue_counts_display#s0    z&SolutionAnnotator.queue_counts_displayc Cs8t|jdd}t|jdd}d}|D]\} } | d| } t| d|j|jd} | ddks;| ddkr=d} |jd| d|d|} || d|d|}| |d}|| d|d}| | d|d}||d}t|||f||f|d tj|| | |fd|j||jtj d |}qd S) a Display the overall statistics for parking lots, object counter etc. Args: im0 (np.ndarray): Inference image. text (Dict[str, Any]): Labels dictionary. txt_color (Tuple[int, int, int]): Display color for text foreground. bg_color (Tuple[int, int, int]): Display color for text background. margin (int): Gap between text and rectangle for better display. rUg{Gz?rg{Gz?z: r)rrrrrN) rQshapeitemsrfrrrrrr)rrStextrbg_colormarginhorizontal_gap vertical_gap text_y_offsetrvaluetxtrrrrect_x1rect_y1rect_x2rect_y2rrrdisplay_analyticsKs$   $z#SolutionAnnotator.display_analyticscCsnt|d|d|d|dt|d|d|d|d}t|dtj}|dkr3|Sd|S)a Calculate the angle between three points for workout monitoring. Args: a (List[float]): The coordinates of the first point. b (List[float]): The coordinates of the second point (vertex). c (List[float]): The coordinates of the third point. Returns: (float): The angle in degrees between the three points. rUrgf@r`)mathatan2abspi)abcradiansanglerrrestimate_pose_anglehsH z%SolutionAnnotator.estimate_pose_angler?c spgdfddt|D}t|dd|ddD]\}}tj|j||ddtjd q|D]}tj|j||d dtjd q3|jS) aD Draw specific keypoints for gym steps counting. Args: keypoints (List[List[float]]): Keypoints data to be plotted, each in format [x, y, confidence]. indices (List[int], optional): Keypoint indices to be plotted. radius (int, optional): Keypoint radius. conf_thresh (float, optional): Confidence threshold for keypoints. Returns: (np.ndarray): Image with drawn keypoints. Note: Keypoint format: [x, y] or [x, y, confidence]. Modifies self.im in-place. )rrcs<g|]\}}|vr|dkrt|dt|dfqS)rrrU)rQ)rir conf_threshindicesrrrs<z8SolutionAnnotator.draw_specific_kpts..NrrUrrr)rrrc) enumerateziprflineryrr) r keypointsrradiusrrstartendptrrrdraw_specific_kptsys "z$SolutionAnnotator.draw_specific_kptshc Cst|d|j|j\\}}}t|j|d|d|df|d|d|d|d|d|jf|dt|j||d|j||j|S)a Draw workout text with a background on the image. Args: display_text (str): The text to be displayed. position (Tuple[int, int]): Coordinates (x, y) on the image where the text will be placed. color (Tuple[int, int, int], optional): Text background color. txt_color (Tuple[int, int, int], optional): Text foreground color. Returns: (int): The height of the text. rrUr r)rfrrrrryr)r display_textpositionrrrr_rrrplot_workout_informations ,z*SolutionAnnotator.plot_workout_informationc Csd|dd|d|}}}||t|dt|df||}||t|dt|d|df||}||t|dt|d||df||dS) a Plot the pose angle, count value, and step stage for workout monitoring. Args: angle_text (str): Angle value for workout monitoring. count_text (str): Counts value for workout monitoring. stage_text (str): Stage decision for workout monitoring. center_kpt (List[int]): Centroid pose index for workout monitoring. color (Tuple[int, int, int], optional): Text background color. txt_color (Tuple[int, int, int], optional): Text foreground color. rCrDzSteps : rrUr](N)rrQ) r angle_text count_text stage_text center_kptrr angle_height count_heightrrrplot_angle_and_count_and_stages$$(z0SolutionAnnotator.plot_angle_and_count_and_stagercrrcc Csd|d}t|d|j|j\\}}}t|jdd|dd|df|ddd|d f} t|j|| d|jd |jtjt|j|d|d |d t |j|dd |dt |j|d d |ddS)a Plot the distance and line between two centroids on the frame. Args: pixels_distance (float): Pixels distance between two bbox centroids. centroids (List[Tuple[int, int]]): Bounding box centroids data. line_color (Tuple[int, int, int], optional): Distance line color. centroid_color (Tuple[int, int, int], optional): Bounding box centroid color. zPixels Distance: rDr)rr]rrrrrUrVN) rfrrrrryrrrr) rpixels_distance centroids line_colorcentroid_colorr text_width_m text_height_mr text_positionrrrplot_distance_and_lines" ( z(SolutionAnnotator.plot_distance_and_linec Cstj|d|j|jdd}||dd} ||dd} | |} | |d|} | |d|} | |}t|t| t| ft| t|fttt|dtj||t| t| fd|jttt||jtj ddS)aA Display the bounding boxes labels in parking management app. Args: im0 (np.ndarray): Inference image. text (str): Object/class name. txt_color (Tuple[int, int, int]): Display color for text foreground. bg_color (Tuple[int, int, int]): Display color for text background. x_center (float): The x position center point for bounding box. y_center (float): The y position center point for bounding box. margin (int): The gap between text and rectangle for better display. rrrrUrrN) rfrrrrrQtuplemaprr)rrSrrrx_centery_centerrrrrrrrrrrrdisplay_objects_labelss0    z(SolutionAnnotator.display_objects_labelsrrc Cst|j|df||f||jd|rit|tj|j|j\\}}}t|j||dd|d|ddf||dd|d|ddf|dt|j|||d|d|dftj|j||jdSdS)a Draw a sweep annotation line and an optional label. Args: line_x (int): The x-coordinate of the sweep line. line_y (int): The y-coordinate limit of the sweep line. label (str, optional): Text label to be drawn in center of sweep line. If None, no label is drawn. color (Tuple[int, int, int]): RGB color for the line and label background. txt_color (Tuple[int, int, int]): RGB color for the label text. rrrrN) rfrryrrFONT_HERSHEY_SIMPLEXrrr) rline_xline_yrrrrrrrrrsweep_annotators(" ""z!SolutionAnnotator.sweep_annotator cCs~t|d|ddt|d|ddf}t|j||jd|dt|j||jd|dt|j||||jdS)a Perform pinpoint human-vision eye mapping and plotting. Args: box (List[float]): Bounding box coordinates in format [x1, y1, x2, y2]. center_point (Tuple[int, int]): Center point for vision eye view. color (Tuple[int, int, int]): Object centroid and line color. pin_color (Tuple[int, int, int]): Visioneye point color. rrrUrVrN)rQrfrryrr)rr[ center_pointr pin_color center_bboxrrr visioneye=s0 zSolutionAnnotator.visioneyerBr r c Cst|dkrtdt|d|dd}t|d|ddt|d|dd}}tt|tj|jd|j d}t|dd|ddd d|} t |j ||f| |d ||dd} ||dd} tj |j t|| | ftj|jd| |||j tjd dS) a Draw a label with a background circle centered within a given bounding box. Args: box (Tuple[float, float, float, float]): The bounding box coordinates (x1, y1, x2, y2). label (str): The text label to be displayed. color (Tuple[int, int, int]): The background color of the circle (B, G, R). txt_color (Tuple[int, int, int]): The color of the text (R, G, B). margin (int): The margin between the text and the circle border. rVzLength of label is z:, only first 3 letters will be used for circle annotation.NrrrUg333333?g?rr)rYrr9rQrfrstrrrrrryr get_txt_colorr) rr[rrrrrrrrequired_radiusrrrrr circle_labelLs&  2"(  zSolutionAnnotator.circle_labelc Cst|d|ddt|d|dd}}t|tj|jd|jd}||dd} ||dd} | |} | |d|} | |d|} | |}t|j| | f| |f|dtj|j|| | ftj|jd| |||jtj ddS) a Draw a label with a background rectangle centered within a given bounding box. Args: box (Tuple[float, float, float, float]): The bounding box coordinates (x1, y1, x2, y2). label (str): The text label to be displayed. color (Tuple[int, int, int]): The background color of the rectangle (B, G, R). txt_color (Tuple[int, int, int]): The color of the text (R, G, B). margin (int): The margin between the text and the rectangle border. rrrUrVg?rrN) rQrfrrrrrryrrr)rr[rrrrrrrrrrrrrrrr text_labelrs&2   zSolutionAnnotator.text_label)NNrvFrw)Nrr)Nrr)Nrr)rr)rr)rrNrr)rr)rBr rr)rBr rr)rqrrrsrtrArrr staticmethodrrrrrrrr rr __classcell__rrr~rrus&&  (     $ ( " &ruc@s eZdZdZddZddZdS)SolutionResultsa A class to encapsulate the results of Ultralytics Solutions. This class is designed to store and manage various outputs generated by the solution pipeline, including counts, angles, and workout stages. Attributes: plot_im (np.ndarray): Processed image with counts, blurred, or other effects from solutions. in_count (int): The total number of "in" counts in a video stream. out_count (int): The total number of "out" counts in a video stream. classwise_count (Dict[str, int]): A dictionary containing counts of objects categorized by class. queue_count (int): The count of objects in a queue or waiting area. workout_count (int): The count of workout repetitions. workout_angle (float): The angle calculated during a workout exercise. workout_stage (str): The current stage of the workout. pixels_distance (float): The calculated distance in pixels between two points or objects. available_slots (int): The number of available slots in a monitored area. filled_slots (int): The number of filled slots in a monitored area. email_sent (bool): A flag indicating whether an email notification was sent. total_tracks (int): The total number of tracked objects. region_counts (dict): The count of objects within a specific region. speed_dict (Dict[str, float]): A dictionary containing speed information for tracked objects. total_crop_objects (int): Total number of cropped objects using ObjectCropper class. cKspd|_d|_d|_i|_d|_d|_d|_d|_d|_d|_ d|_ d|_ d|_ i|_ i|_d|_|j|dS)z Initialize a SolutionResults object with default or user-specified values. Args: **kwargs (Any): Optional arguments to override default attribute values. NrF)rkin_count out_countclasswise_count queue_count workout_count workout_angle workout_stageravailable_slots filled_slots email_sent total_tracks region_counts speed_dicttotal_crop_objects__dict__r5)rr?rrrrAs"zSolutionResults.__init__cCs4dd|jD}dddd|DdS)z Return a formatted string representation of the SolutionResults object. Returns: (str): A string representation listing non-null attributes. cSs0i|]\}}|dkr|didddfvr||qS)rkNrrFrrrvrrrrs z+SolutionResults.__str__..zSolutionResults(z, css"|] \}}|d|VqdS)=Nrr%rrr s z*SolutionResults.__str__..))r$rjoin)rattrsrrr__str__s zSolutionResults.__str__N)rqrrrsrtrAr,rrrrrs r)r collectionsrrfnumpyr ultralyticsrultralytics.utilsrrrrultralytics.utils.checksrr ultralytics.utils.plottingr r rurrrrrs   Q<