Pistage et estimation du mouvement

Flux optique, reconnaissance d’activité, estimation du mouvement, réidentification d’objets et pistage

L’estimation du mouvement et le pistage sont des opérations essentielles dans de nombreuses applications de Computer Vision comme la reconnaissance d’activité, le contrôle du trafic, la sécurité automobile et la surveillance.

Computer Vision Toolbox™ propose des algorithmes de pistage vidéo tels que CAMShift (Continuously Adaptive Mean Shift) et KLT (Kanade-Lucas-Tomasi). Vous pouvez utiliser ces algorithmes pour pister un seul objet ou comme blocs de base dans un système de pistage plus complexe. La toolbox propose également un framework pour le pistage de plusieurs objets. Celui-ci comprend un filtre de Kalman ainsi que l’utilisation de l’algorithme hongrois pour affecter les détections d’objets à des pistes.

L’estimation du mouvement est le processus consistant à déterminer le mouvement des blocs entre des trames vidéo adjacentes. Cette toolbox propose des algorithmes d’estimation du mouvement tels que le flux optique et la correspondance de bloc et de modèle. Ces algorithmes créent des vecteurs de mouvement se rapportant à l’image entière, à des blocs, à des formes arbitraires ou à des pixels particuliers. Pour la correspondance de blocs et de modèles, les métriques d’évaluation permettant de trouver la meilleure correspondance sont notamment l’erreur quadratique moyenne (MSE), l’écart absolu moyen (MAD), la différence absolue maximale (MaxAD), la somme des différences absolues (SAD) et la somme des carrés des différences (SSD).

Fonctions

développer tout

Charger, enregistrer et afficher des vidéos

`vision.BinaryFileReader`	Read video data from binary files
`vision.BinaryFileWriter`	Write binary video data to files
`vision.DeployableVideoPlayer`	Display video
`vision.VideoPlayer`	Play video or display image
`vision.VideoFileWriter`	Write video frames and audio samples to video file
`VideoReader`	Create object to read video files

Pistage d'objets

`assignDetectionsToTracks`	Assign detections to tracks for multiobject tracking
`bbox2points`	Convert rectangle to corner points list
`configureKalmanFilter`	Create Kalman filter for object tracking
`vision.KalmanFilter`	Correction of measurement, state, and state estimation error covariance
`vision.HistogramBasedTracker`	Histogram-based object tracking
`vision.PointTracker`	Track points in video using Kanade-Lucas-Tomasi (KLT) algorithm
`vision.BlockMatcher`	Estimate motion between images or video frames
`vision.TemplateMatcher`	Locate template in image

Réidentification d’objets

`reidentificationNetwork`	Re-identification deep learning network for re-identifying and tracking objects (depuis R2024a)
`extractReidentificationFeatures`	Extract object re-identification (ReID) features from image (depuis R2024a)
`trainReidentificationNetwork`	Train re-identification (ReID) deep learning network (depuis R2024a)
`evaluateReidentificationNetwork`	Evaluate re-identification network using cumulative matching characteristic (CMC) and mean average precision (mAP) metrics (depuis R2024a)
`reidentificationMetrics`	Re-identification (ReID) quality metrics (depuis R2024a)

Estimation du mouvement

`opticalFlow`	Object for storing optical flow matrices
`opticalFlowFarneback`	Object for estimating optical flow using Farneback method
`opticalFlowHS`	Object for estimating optical flow using Horn-Schunck method
`opticalFlowLK`	Object for estimating optical flow using Lucas-Kanade method
`opticalFlowLKDoG`	Object for estimating optical flow using Lucas-Kanade derivative of Gaussian method
`vision.BlockMatcher`	Estimate motion between images or video frames
`vision.TemplateMatcher`	Locate template in image

Visualisation et affichage

`insertMarker`	Insert markers in image or video
`insertShape`	Insert shapes in image or video
`insertObjectAnnotation`	Annotate truecolor or grayscale image or video
`insertText`	Insert text in image or video
`imshow`	Display image
`imshowpair`	Compare differences between images

Rubriques

Multiple Object Tracking
Locate a moving object or multiple objects over time in a video stream.

Exemples présentés

Reidentify People Throughout a Video Sequence Using ReID Network

Track people throughout a video sequence using re-identification with a residual network.

Ouvrir le live script

Automate Ground Truth Labeling for Object Tracking and Re-Identification

Create an automation algorithm to automatically label data for object tracking and for object re-identification.

Ouvrir le live script

Convert Ground Truth Labeling Data for Object Tracking

Convert a groundTruth object to the trackCLEARmetrics truth format.

Ouvrir le live script

Multi-Object Tracking with DeepSORT

Integrate appearance features from a re-Identification (Re-ID) deep neural network with a multi-object tracker.

Ouvrir le live script

Tracking Pedestrians from a Moving Car

Track pedestrians using a camera mounted in a moving car.

Ouvrir le script

Motion-Based Multiple Object Tracking

Perform automatic detection and motion-based tracking of moving objects in a video from a stationary camera.

Ouvrir le script

Visual Tracking of Occluded and Unresolved Objects

Resolve challenging tracking scenarios when objects are occluded or when they are in close proximity to each other.

Ouvrir le live script

Implement Simple Online and Realtime Tracking

Implement the Simple Online and Realtime (SORT) object tracking algorithm using the Computer Vision Toolbox and the Sensor Fusion and Tracking Toolbox™.

Ouvrir le live script

Track a Face in Scene

Track a face using a minimum Eigen features detection function and a point tracker.

Ouvrir le script

Face Detection and Tracking Using Live Video Acquisition

Automatically detect and track a face in a live video stream, using the KLT algorithm.

Ouvrir le script

Face Detection and Tracking Using CAMShift

Automatically detect and track a face.

Ouvrir le script

Face Detection and Tracking Using the KLT Algorithm

Automatically detect and track a face using feature points. The approach in this example keeps track of the face even when the person tilts his or her head, or moves toward or away from the camera.

Ouvrir le live script

Use Kalman Filter for Object Tracking

Use the vision.KalmanFilter object and configureKalmanFilter function to track objects.

Ouvrir le script

Import Camera-Based Datasets in MOT Challenge Format for Object Tracking

Read camera image sequences and convert the ground truth and detections to Sensor Fusion and Tracking Toolbox formats using a custom dataset.

Ouvrir le live script

Multi-Object Tracking and Human Pose Estimation

Detect multiple people, track them, and estimate their body poses in a video by using pretrained deep learning networks and a global nearest-neighbor (GNN) assignment tracking approach.

Ouvrir le live script