Multi-Object Tracking

The nuScenes dataset is a large-scale autonomous driving dataset. The dataset has 3D bounding boxes for 1000 scenes collected in Boston and Singapore. Each scene is 20 seconds long and annotated at 2Hz. This results in a total of 28130 samples for training, 6019 samples for validation and 6008 samples for testing. The dataset has the full autonomous vehicle data suite: 32-beam LiDAR, 6 cameras and radars with complete 360° coverage. The 3D object detection challenge evaluates the performance on 10 classes: cars, trucks, buses, trailers, construction vehicles, pedestrians, motorcycles, bicycles, traffic cones and barriers. Source: PointPainting: Sequential Fusion for 3D Object Detection

The Waymo Open Dataset is comprised of high resolution sensor data collected by autonomous vehicles operated by the Waymo Driver in a wide variety of conditions. The Waymo Open Dataset currently contains 1,950 segments. The authors plan to grow this dataset in the future. Currently the datasets includes: * 1,950 segments of 20s each, collected at 10Hz (390,000 frames) in diverse geographies and conditions * Sensor data * 1 mid-range lidar * 4 short-range lidars * 5 cameras (front and sides) * Synchronized lidar and camera data * Lidar to camera projections * Sensor calibrations and vehicle poses * Labeled data * Labels for 4 object classes - Vehicles, Pedestrians, Cyclists, Signs * High-quality labels for lidar data in 1,200 segments * 12.6M 3D bounding box labels with tracking IDs on lidar data * High-quality labels for camera data in 1,000 segments * 11.8M 2D bounding box labels with tracking IDs on camera data

Datasets drive vision progress, yet existing driving datasets are impoverished in terms of visual content and supported tasks to study multitask learning for autonomous driving. Researchers are usually constrained to study a small set of problems on one dataset, while real-world computer vision applications require performing tasks of various complexities. We construct BDD100K, the largest driving video dataset with 100K videos and 10 tasks to evaluate the exciting progress of image recognition algorithms on autonomous driving. The dataset possesses geographic, environmental, and weather diversity, which is useful for training models that are less likely to be surprised by new conditions. Based on this diverse dataset, we build a benchmark for heterogeneous multitask learning and study how to solve the tasks together. Our experiments show that special training strategies are needed for existing models to perform such heterogeneous tasks. BDD100K opens the door for future studies in this important venue. More detail is at the dataset home page.

The Multiple Object Tracking 17 (MOT17) dataset is a dataset for multiple object tracking. Similar to its previous version MOT16, this challenge contains seven different indoor and outdoor scenes of public places with pedestrians as the objects of interest. A video for each scene is divided into two clips, one for training and the other for testing. The dataset provides detections of objects in the video frames with three detectors, namely SDP, Faster-RCNN and DPM. The challenge accepts both on-line and off-line tracking approaches, where the latter are allowed to use the future video frames to predict tracks. Source: Deep Affinity Network for Multiple Object Tracking Image Source: https://www.researchgate.net/figure/Visualization-of-selected-sequences-from-the-MOT17-benchmark-dataset_fig4_337133502

The MOTChallenge datasets are designed for the task of multiple object tracking. There are several variants of the dataset released each year, such as MOT15, MOT17, MOT20. Source: MOTChallenge 2015: Towards a Benchmark for Multi-Target Tracking

The MOT16 dataset is a dataset for multiple object tracking. It a collection of existing and new data (part of the sources are from and ), containing 14 challenging real-world videos of both static scenes and moving scenes, 7 for training and 7 for testing. It is a large-scale dataset, composed of totally 110407 bounding boxes in training set and 182326 bounding boxes in test set. All video sequences are annotated under strict standards, their ground-truths are highly accurate, making the evaluation meaningful. Source: SOT for MOT Image Source: https://www.researchgate.net/figure/Sample-results-on-the-sequence-MOT16-07-encoded-as-in-the-previous-figure-Table-1_fig3_309641746

Virtual KITTI is a photo-realistic synthetic video dataset designed to learn and evaluate computer vision models for several video understanding tasks: object detection and multi-object tracking, scene-level and instance-level semantic segmentation, optical flow, and depth estimation. Virtual KITTI contains 50 high-resolution monocular videos (21,260 frames) generated from five different virtual worlds in urban settings under different imaging and weather conditions. These worlds were created using the Unity game engine and a novel real-to-virtual cloning method. These photo-realistic synthetic videos are automatically, exactly, and fully annotated for 2D and 3D multi-object tracking and at the pixel level with category, instance, flow, and depth labels (cf. below for download links). Source: https://europe.naverlabs.com/research/computer-vision/proxy-virtual-worlds-vkitti-1/ Image Source: https://arxiv.org/pdf/1605.06457.pdf

UAVDT is a large scale challenging UAV Detection and Tracking benchmark (i.e., about 80, 000 representative frames from 10 hours raw videos) for 3 important fundamental tasks, i.e., object DETection (DET), Single Object Tracking (SOT) and Multiple Object Tracking (MOT). The dataset is captured by UAVs in various complex scenarios. The objects of interest in this benchmark are vehicles. The frames are manually annotated with bounding boxes and some useful attributes, e.g., vehicle category and occlusion. The UAVDT benchmark consists of 100 video sequences, which are selected from over 10 hours of videos taken with an UAV platform at a number of locations in urban areas, representing various common scenes including squares, arterial streets, toll stations, highways, crossings and T-junctions. The videos are recorded at 30 frames per seconds (fps), with the JPEG image resolution of 1080 × 540 pixels.

A large-scale multi-object tracking dataset for human tracking in occlusion, frequent crossover, uniform appearance and diverse body gestures. It is proposed to emphasize the importance of motion analysis in multi-object tracking instead of mainly appearance-matching-based diagram.

MOT2015 is a dataset for multiple object tracking. It contains 11 different indoor and outdoor scenes of public places with pedestrians as the objects of interest, where camera motion, camera angle and imaging condition vary greatly. The dataset provides detections generated by the ACF-based detector. Source: FAMNet: Joint Learning of Feature, Affinity and Multi-dimensional Assignment for Online Multiple Object Tracking Image Source: https://www.researchgate.net/figure/Exemplary-qualitative-tracking-results-for-the-MOT15-benchmark-dataset-a-d-are-from-a_fig1_340328377

Wildtrack is a large-scale and high-resolution dataset. It has been captured with seven static cameras in a public open area, and unscripted dense groups of pedestrians standing and walking. Together with the camera frames, we provide an accurate joint (extrinsic and intrinsic) calibration, as well as 7 series of 400 annotated frames for detection at a rate of 2 frames per second. This results in over 40 000 bounding boxes delimiting every person present in the area of interest, for a total of more than 300 individuals.

Virtual KITTI 2 is an updated version of the well-known Virtual KITTI dataset which consists of 5 sequence clones from the KITTI tracking benchmark. In addition, the dataset provides different variants of these sequences such as modified weather conditions (e.g. fog, rain) or modified camera configurations (e.g. rotated by 15◦). For each sequence we provide multiple sets of images containing RGB, depth, class segmentation, instance segmentation, flow, and scene flow data. Camera parameters and poses as well as vehicle locations are available as well. In order to showcase some of the dataset’s capabilities, we ran multiple relevant experiments using state-of-the-art algorithms from the field of autonomous driving. The dataset is available for download at https://europe.naverlabs.com/Research/Computer-Vision/Proxy-Virtual-Worlds.

TAO is a federated dataset for Tracking Any Object, containing 2,907 high resolution videos, captured in diverse environments, which are half a minute long on average. A bottom-up approach was used for discovering a large vocabulary of 833 categories, an order of magnitude more than prior tracking benchmarks. The dataset was annotated by labelling tracks for objects that move at any point in the video, and giving names to them post factum. Source: TAO: A Large-Scale Benchmark for Tracking Any Object

MOT20 is a dataset for multiple object tracking. The dataset contains 8 challenging video sequences (4 train, 4 test) in unconstrained environments, from crowded places such as train stations, town squares and a sports stadium. Image Source: https://motchallenge.net/vis/MOT20-04

A novel egocentric dataset collected from social mobile manipulator JackRabbot. The dataset includes 64 minutes of annotated multimodal sensor data including stereo cylindrical 360 degrees RGB video at 15 fps, 3D point clouds from two Velodyne 16 Lidars, line 3D point clouds from two Sick Lidars, audio signal, RGB-D video at 30 fps, 360 degrees spherical image from a fisheye camera and encoder values from the robot's wheels. Source: JRDB: A Dataset and Benchmark of Egocentric Visual Perception for Navigation in Human Environments

Motivation Multi-object tracking (MOT) is a fundamental task in computer vision, aiming to estimate objects (e.g., pedestrians and vehicles) bounding boxes and identities in video sequences. Prevailing human-tracking MOT datasets mainly focus on pedestrians in crowded street scenes (e.g., MOT17/20) or dancers in static scenes (DanceTrack). In spite of the increasing demands for sports analysis, there is a lack of multi-object tracking datasets for a variety of sports scenes, where the background is complicated, players possess rapid motion and the camera lens moves fast. To this purpose, we propose a large-scale multi-object tracking dataset named SportsMOT, consisting of 240 video clips from 3 categories (i.e., basketball, football and volleyball). The objective is to only track players on the playground (i.e., except for a number of spectators, referees and coaches) in various sports scenes. We expect SportsMOT to encourage the community to concentrate more on the complicated sports scenes. ## Characteristics - Large scale - Fine Annotations - Player id consistency - No shot change - High and fixed resolution(1080P) - ... ## Focus - Diverse sports scenes - Complex motion patterns - Challenging re-id ## Download ### Examples You can download the example for SportsMOT. - OneDrive - Baidu Netdisk, password: 4dnw ### Official Dataset Please Sign up in codalab, and participate in our competition. Download links are available in Participate/Get Data. ## News - SportsMOT is used for DeeperAction@ECCV-2022. - Refer to github repo: MCG-NJU/SportsMOT for the latest info.

The Multi-Object and Segmentation (MOTS) benchmark [2] consists of 21 training sequences and 29 test sequences. It is based on the KITTI Tracking Evaluation 2012 and extends the annotations to the Multi-Object and Segmentation (MOTS) task. To this end, we added dense pixel-wise segmentation labels for every object. We evaluate submitted results using the metrics HOTA, CLEAR MOT, and MT/PT/ML. We rank methods by HOTA [1]. Our development kit and GitHub evaluation code provide details about the data format as well as utility functions for reading and writing the label files. (adapted for the segmentation case). Evaluation is performed using the code from the TrackEval repository. [1] J. Luiten, A. Os̆ep, P. Dendorfer, P. Torr, A. Geiger, L. Leal-Taixé, B. Leibe: HOTA: A Higher Order Metric for Evaluating Multi-object Tracking. IJCV 2020. [2] P. Voigtlaender, M. Krause, A. Os̆ep, J. Luiten, B. Sekar, A. Geiger, B. Leibe: MOTS: Multi-Object Tracking and Segmentation. CVPR 2019.

MultiviewX is a synthetic Multiview pedestrian detection dataset. It is build using pedestrian models from PersonX, in Unity. The MultiviewX dataset covers a square of 16 meters by 25 meters. The ground plane is quantized into a 640x1000 grid. There are 6 cameras with overlapping field-of-view in the MultiviewX dataset, each of which outputs a 1080x1920 resolution image. On average, 4.41 cameras are covering the same location. Source: https://github.com/hou-yz/MVDet Image Source: https://github.com/hou-yz/MVDet

Argoverse-HD is a dataset built for streaming object detection, which encompasses real-time object detection, video object detection, tracking, and short-term forecasting. It contains the video data from Argoverse 1.1 with our own MS COCO-style bounding box annotations with track IDs. The annotations are backward-compatible with COCO as one can directly evaluate COCO pre-trained models on this dataset to estimate the efficiency or the cross-dataset generalization capability of the models. The dataset contains high-quality and temporally-dense annotations for high-resolution videos (1920 x 1200 @ 30 FPS). Overall, there are 70,000 image frames and 1.3 million bounding boxes. Argoverse-HD is the dataset used in the Streaming Perception Challenge, which includes two tracks: - Detection-only (real-time object detection). In this track, the participants will develop single-frame object detectors as they would for COCO and LVIS challenges. The crucial distinction is that the evaluation will score latency through streaming accuracy. - Full-stack. In this track, the method is unrestricted. However, most likely tracking and forecasting will be used to compensate for the latency of the detectors. By default, all submissions measure their latency on a V100 GPU with the official toolkit.

A new large-scale dataset for understanding human motions, poses, and actions in a variety of realistic events, especially crowd & complex events. It contains a record number of poses (>1M), the largest number of action labels (>56k) for complex events, and one of the largest number of trajectories lasting for long terms (with average trajectory length >480). Besides, an online evaluation server is built for researchers to evaluate their approaches. Source: Human in Events: A Large-Scale Benchmark for Human-centric Video Analysis in Complex Events

SeaDronesSee is a large-scale data set aimed at helping develop systems for Search and Rescue (SAR) using Unmanned Aerial Vehicles (UAVs) in maritime scenarios. Building highly complex autonomous UAV systems that aid in SAR missions requires robust computer vision algorithms to detect and track objects or persons of interest. This data set provides three sets of tracks: object detection, single-object tracking and multi-object tracking. Each track consists of its own data set and leaderboard. Object Detection: 5,630 train images, 859 validation images, 1,796 testing images Single-Object Tracking: 58 training video clips, 70 validation video clips and 80 testing video clips Multi-Object Tracking: 22 video clips with 54,105 frames Additionally, we provide multi-spektral footage: Multi-Spektral Object Detection: 246 train images, 61 validation images, 125 testing images We will continue to update this data set to make it more versatile and reflect real-world requirements in dynamic situations.

GMOT-40 is the first public dense dataset for Generic Multiple Object Tracking (GMOT). It contains 40 carefully annotated sequences evenly distributed among 10 object categories. Beyond the data, a challenging protocal, one-shot GMOT, is adopted and a series of baseline algorithms is introduced. GMOT-40 is featured in Dense objects. Over 80 objects of the same class could appear in one frame. High-quality label. Manual annotation with careful inspection in each frame. Diversity in target. Large variability between classes and within the sequences of the same class. Real world challenges. Occlusion, target enter/exiting, motion blur, deformation and so on. Challenging protocol. One-shot GMOT protocol is adopted for evaluation. New baselines. A series of baseline methods for one-shot GMOT task is introduced.

Robust detection and tracking of objects is crucial for the deployment of autonomous vehicle technology. Image based benchmark datasets have driven development in computer vision tasks such as object detection, tracking and segmentation of agents in the environment. Most autonomous vehicles, however, carry a combination of cameras and range sensors such as lidar and radar. As machine learning based methods for detection and tracking become more prevalent, there is a need to train and evaluate such methods on datasets containing range sensor data along with images. In this work we present nuTonomy scenes (nuScenes), the first dataset to carry the full autonomous vehicle sensor suite: 6 cameras, 5 radars and 1 lidar, all with full 360 degree field of view. nuScenes comprises 1000 scenes, each 20s long and fully annotated with 3D bounding boxes for 23 classes and 8 attributes. It has 7x as many annotations and 100x as many images as the pioneering KITTI dataset. We define novel 3D detection and tracking metrics. We also provide careful dataset analysis as well as baselines for lidar and image based detection and tracking. Data, development kit and more information are available online.

The AI City Challenge, hosted at CVPR 2024, focuses on harnessing AI to enhance operational efficiency in physical settings such as retail and warehouse environments, and Intelligent Traffic Systems (ITS). It aims to utilize AI for actionable insights from sensor data, like camera feeds, to improve traffic safety and transportation outcomes. This year, the challenge spotlights two key areas with significant potential: retail business and ITS.

PathTrack is a dataset for person tracking which contains more than 15,000 person trajectories in 720 sequences. Source: PathTrack: Fast Trajectory Annotation with Path Supervision

Are current 3D object tracking methods truely robust enough for low-fidelity depth sensors like the iPhone LiDAR? We introduce DTTD-Mobile (fully compatible w/ YCB toolbox), a new benchmark built on real-world data captured from mobile devices; 18 objects observed in 100 videos with 47,668 sampled frames and 114,143 object annotations. We evaluate several popular methods—including BundleSDF, ES6D, MegaPose, and DenseFusion—and highlight their limitations in this challenging setting. Keywords: ObjectPoseEstimation, MobileAI, EdgeAI, ARVR, CVPR

Multi-camera Multiple People Tracking (MMPTRACK) dataset has about 9.6 hours of videos, with over half a million frame-wise annotations. The dataset is densely annotated, e.g., per-frame bounding boxes and person identities are available, as well as camera calibration parameters. Our dataset is recorded with 15 frames per second (FPS) in five diverse and challenging environment settings., e.g., retail, lobby, industry, cafe, and office. This is by far the largest publicly available multi-camera multiple people tracking dataset. We expect the availability of such large-scale multi-camera multiple people tracking dataset will encourage more participants in this research topic. This dataset is also valuable for the evaluation of other tasks, such as multi-view people detection and monocular multiple people tracking.

Video object segmentation has been studied extensively in the past decade due to its importance in understanding video spatial-temporal structures as well as its value in industrial applications. Recently, data-driven algorithms (e.g. deep learning) have become the dominant approach to computer vision problems and one of the most important keys to their successes is the availability of large-scale datasets. Previously, we presented the first large-scale video object segmentation dataset named YouTubeVOS and hosted the Large-scale Video Object Segmentation Challenge in conjuction with ECCV 2018, ICCV 2019 and CVPR 2021. This year, we are thrilled to invite you to the 4th Large-scale Video Object Segmentation Challenge in conjunction with CVPR 2022. The benchmark would be an augmented version of the YouTubeVOS dataset with more annotations. Some incorrect annotations are also corrected. For more details, check our website for the workshop and challenge.

The dataset is designed specifically to solve a range of computer vision problems (2D-3D tracking, posture) faced by biologists while designing behavior studies with animals. Typically, datasets for animal-specific vision tasks are created using open-source video material. This might be effective for an initial start, but these methods are not deployment ready for the behavior community. Therefore, we designed a semi-automated method for biologists to create well-curated datasets at a large scale for the ML and Vision community. 3D-POP is the first dataset with 3D ground truth for multi-animal, multi-view tracking problems. Highlight: The dataset is captured with the intention of using it for various vision problems and with different levels of complexity (no of cameras, no of individuals) Video explanation: Link to YouTube video Video teaser: Link to YouTube video ## Dataset Features: ### Marker-based videos: - 6 hours+ of annotations of 18 individuals (groups of 1, 2, 5, 10). - Bounding box - Trajectories (2D and 3D) - Posture (2D and 3D) with 9 key points - Identities - Total of 57 sequences (4K) with 4 views. - Dataset customization* (Users can modify the dataset and add key points to the dataset) ### Markerless: - 1Hr+ videos of 18 individuals in groups of 1, 2, 5, 11. The birds have no markers. This data is provided as test cases and unsupervised approaches. ## Problems: ### 2D domain: - Position, Posture of birds (different group sizes n = 1, 2, 5, 10) with Single/Multiview. - Tracking with single - multiview ### 3D domain: - Position, Posture of birds (different group sizes n = 1, 2, 5, 10) with Single/Multiview. - Tracking with single - multiview ### Fine-grained recognition: - Identity tracking with ground truth. ### Unsupervised learning: - 2D or 3D posture problems ## Idea: The dataset is created with a motion capture system, using the 6-DOF tracking ability. Assumptions are that head and body act as rigid bodies when birds walk and forage (proved with experiment). Therefore, we get the 3D position of key points by tracking head/body orientation.

It contains about 28K medium quality animal images belonging to 10 categories: dog, cat, horse, spyder, butterfly, chicken, sheep, cow, squirrel, and elephant. All the images have been collected from "google images" and have been checked by humans. There is some erroneous data to simulate real conditions (eg. images taken by users of your app). The main directory is divided into folders, one for each category. The image count for each category varies from 2K to 5 K units.

DIVOTrack is a cross-view multi-object tracking dataset for DIVerse Open scenes with dense tracking pedestrians in realistic and non-experimental environments. DIVOTrack has ten distinct scenarios and 550 cross-view tracks. Source: DIVOTrack: A Novel Dataset and Baseline Method for Cross-View Multi-Object Tracking in DIVerse Open Scenes Image Source: https://github.com/shengyuhao/DIVOTrack

One of the recent trends in vision problems is to use natural language captions to describe the objects of interest. This approach can overcome some limitations of traditional methods that rely on bounding boxes or category annotations. This paper introduces a novel paradigm for Multiple Object Tracking called Type-to-Track, which allows users to track objects in videos by typing natural language descriptions. We present a new dataset for that Grounded Multiple Object Tracking task, called GroOT, that contains videos with various types of objects and their corresponding textual captions of 256K words describing their appearance and action in detail. To cover a diverse range of scenes, GroOT was created using official videos and bounding box annotations from the MOT17, TAO and MOT20.

The RailEye3D dataset, a collection of train-platform scenarios for applications targeting passenger safety and automation of train dispatching, consists of 10 image sequences captured at 6 railway stations in Austria. Annotations for multi-object tracking are provided in both an unified format as well as the ground-truth format used in the MOTChallenge.

The SoccerNet Game State Reconstruction task is a novel high level computer vision task that is specific to sports analytics. It aims at recognizing the state of a sport game, i.e., identifying and localizing all sports individuals (players, referees, ..) on the field based on a raw input videos. SoccerNet-GSR is composed of 200 video sequences of 30 seconds, annotated with 9.37 million line points for pitch localization and camera calibration, as well as over 2.36 million athlete positions on the pitch with their respective role, team, and jersey number.

Synthehicle is a massive CARLA-based synthehic multi-vehicle multi-camera tracking dataset and includes ground truth for 2D detection and tracking, 3D detection and tracking, depth estimation, and semantic, instance and panoptic segmentation.

We collected 32 videos that record bee colony activity from different periods on several sunny days. The total size of the dataset is 3,562 frames and 43,169 annotations.