Online Domain Adaptation for Multi-Object Tracking

Gaidon, Adrien; Vig, Eleonora

doi:10.5244/c.29.3

Cited by 20 publications

(10 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thanks to the recent progress on object detection, association-based tracking-by-detection in monocular video streams is particularly successful and widely used for MOT [29,30,31,32,33,34,35,36,37,38] (see [39] for a recent review). These methods consist in building tracks by linking object detections through time.…”

Section: Strong Deep Learning Baselines For Motmentioning

confidence: 99%

VirtualWorlds as Proxy for Multi-object Tracking Analysis

Gaidon

Wang

Cabon

et al. 2016

2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Self Cite

816

738

View full text Add to dashboard Cite

Modern computer vision algorithms typically require expensive data acquisition and accurate manual labeling. In this work, we instead leverage the recent progress in computer graphics to generate fully labeled, dynamic, and photo-realistic proxy virtual worlds. We propose an efficient real-to-virtual world cloning method, and validate our approach by building and publicly releasing a new video dataset, called "Virtual KITTI" 1 , automatically labeled with accurate ground truth for object detection, tracking, scene and instance segmentation, depth, and optical flow. We provide quantitative experimental evidence suggesting that (i) modern deep learning algorithms pre-trained on real data behave similarly in real and virtual worlds, and (ii) pre-training on virtual data improves performance. As the gap between real and virtual worlds is small, virtual worlds enable measuring the impact of various weather and imaging conditions on recognition performance, all other things being equal. We show these factors may affect drastically otherwise high-performing deep models for tracking.

show abstract

Section: Strong Deep Learning Baselines For Motmentioning

confidence: 99%

VirtualWorlds as Proxy for Multi-object Tracking Analysis

Gaidon

Wang

Cabon

et al. 2016

2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Self Cite

816

738

View full text Add to dashboard Cite

show abstract

“…We evaluate the performance of the proposed method on KITTI tracking benchmark. Quantitative results are shown in Table 2 [ 17–27 ] , and some exemplars of the tracking results from the proposed method in KITTI dataset are shown in Fig 5…”

Section: Resultsmentioning

confidence: 99%

Multi‐Traffic Targets Tracking Based on an Improved Structural Sparse Representation with Spatial‐Temporal Constraint

Yang

SHANG

et al. 2022

Chinese J of Electronics

View full text Add to dashboard Cite

Vehicles or pedestrians tracking is an important task in intelligent transportation system. In this paper, we propose an online multi‐object tracking for intelligent traffic platform that employs improved sparse representation and structural constraint. We first build the spatial‐temporal constraint via the geometric relations and appearance of tracked objects, then we construct a robust appearance model by incorporating the discriminative sparse representation with weight constraint and local sparse appearance with occlusion analysis. Finally, we complete data association by using maximum a posteriori in a Bayesian framework in the pursuit for the optimal detection estimation. Experimental results in two challenging vehicle tracking benchmark datasets show that the proposed method has a good tracking performance.

show abstract

“…A possible solution is to create a generic detector adapted for a specific video by tuning some parameters. Previous works for multiple people tracking include [91], [39]. b) MTT with Deep Learning: Deep learning has proven to be a high performance method for classification, detection and many computer visions tasks.…”

Section: Multiple Pedestrian Trackingmentioning

confidence: 99%

Pedestrian Models for Autonomous Driving Part I: Low-Level Models, From Sensing to Tracking

Camara

Bellotto

Coşar

et al. 2021

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

Autonomous vehicles (AVs) must share space with pedestrians, both in carriageway cases such as cars at pedestrian crossings and off-carriageway cases such as delivery vehicles navigating through crowds on pedestrianized high-streets. Unlike static obstacles, pedestrians are active agents with complex, interactive motions. Planning AV actions in the presence of pedestrians thus requires modelling of their probable future behaviour as well as detecting and tracking them. This narrative review article is Part I of a pair, together surveying the current technology stack involved in this process, organising recent research into a hierarchical taxonomy ranging from low-level image detection to high-level psychology models, from the perspective of an AV designer. This self-contained Part I covers the lower levels of this stack, from sensing, through detection and recognition, up to tracking of pedestrians. Technologies at these levels are found to be mature and available as foundations for use in high-level systems, such as behaviour modelling, prediction and interaction control.

show abstract

Online Domain Adaptation for Multi-Object Tracking

Cited by 20 publications

References 43 publications

VirtualWorlds as Proxy for Multi-object Tracking Analysis

VirtualWorlds as Proxy for Multi-object Tracking Analysis

Multi‐Traffic Targets Tracking Based on an Improved Structural Sparse Representation with Spatial‐Temporal Constraint

Pedestrian Models for Autonomous Driving Part I: Low-Level Models, From Sensing to Tracking

Contact Info

Product

Resources

About