scholarly journals A Hierarchical Association Framework for Multi-Object Tracking in Airborne Videos

2018 ◽  
Author(s):  
Ting Chen ◽  
Andrea Pennisi ◽  
Zhi Li ◽  
Yanning Zhang ◽  
Hichem Sahli
Keyword(s):  
Object Tracking ◽  
Target Tracking ◽  
Moving Objects ◽  
Data Association ◽  
Multiple Object Tracking ◽  
Challenging Problem ◽  
Compressive Tracking ◽  
Vehicle Motion ◽  
Airborne Vehicle ◽  
State Of Art

Multi-object tracking (MOT) in airborne videos is a challenging problem due to the uncertain airborne vehicle motion, vibrations of the mounted camera, unreliable detections, size, appearance and motion of the moving objects as well as occlusions due to the interaction between the moving objects and with other static objects in the scene.To deal with these problems, this work proposes a four-stage Hierarchical Association framework for multiple object Tracking in Airborne video (HATA). The proposed framework combines data association-based tracking (DAT) methods and target tracking using a Compressive Tracking approach, to robustly track objects in complex airborne surveillance scenes. In each association stage, different sets of tracklets and detections are associated to efficiently handle local tracklet generation, local trajectory construction, global drifting tracklet correction and global fragmented tracklet linking. Experiments with challenging airborne video datasets show significant tracking improvement compared to existing state-of-art methods.

scholarly journals A Hierarchical Association Framework for Multi-Object Tracking in Airborne Videos

2018 ◽  
Vol 10 (9) ◽  
pp. 1347 ◽  
Author(s):  
Ting Chen ◽  
Andrea Pennisi ◽  
Zhi Li ◽  
Yanning Zhang ◽  
Hichem Sahli
Keyword(s):  
Object Tracking ◽  
Target Tracking ◽  
Moving Objects ◽  
State Of The Art ◽  
Data Association ◽  
Multiple Object Tracking ◽  
Challenging Problem ◽  
Compressive Tracking ◽  
Vehicle Motion ◽  
Airborne Vehicle

Multi-Object Tracking (MOT) in airborne videos is a challenging problem due to the uncertain airborne vehicle motion, vibrations of the mounted camera, unreliable detections, changes of size, appearance and motion of the moving objects and occlusions caused by the interaction between moving and static objects in the scene. To deal with these problems, this work proposes a four-stage hierarchical association framework for multiple object tracking in airborne video. The proposed framework combines Data Association-based Tracking (DAT) methods and target tracking using a compressive tracking approach, to robustly track objects in complex airborne surveillance scenes. In each association stage, different sets of tracklets and detections are associated to efficiently handle local tracklet generation, local trajectory construction, global drifting tracklet correction and global fragmented tracklet linking. Experiments with challenging airborne videos show significant tracking improvement compared to existing state-of-the-art methods.

An New Method for Multi-Object Tracking Using Energy Minimization-Based Data Association

2013 ◽  
Vol 427-429 ◽  
pp. 1822-1825
Author(s):  
Zhen Hai Wang ◽  
Ki Cheon Hong
Keyword(s):  
Object Tracking ◽  
Energy Minimization ◽  
Moving Objects ◽  
Data Association ◽  
Multiple Object Tracking ◽  
Object Extraction ◽  
Frame Difference ◽  
Multiple Object ◽  
Important Research Topic ◽  
Key Steps

multiple object tracking is an active and important research topic. It faces many challenging problems. Object extraction and data association are two most key steps in multiple object tracking. To improve tracking performance, this paper proposed a tracking method which combines Kalman filter and energy minimization-based data association. Moving objects are segmented through frame difference. Its can be consider as the vertex. All detections in adjacent frames are be used to construct a graph. The energy is finally minimized with a graph cuts optimization. Data association can be consider as multiple labeling problems. Object corresponding can be obtained through energy minimization. Experiment results demonstrate this method can be accurately tracking two moving objects.

Distractor Locations Influence Multiple Object Tracking Beyond Interobject Spacing

2015 ◽  
Vol 62 (3) ◽  
pp. 170-180 ◽  
Author(s):  
Hauke S. Meyerhoff ◽  
Frank Papenmeier ◽  
Georg Jahn ◽  
Markus Huff
Keyword(s):  
Object Tracking ◽  
Target Tracking ◽  
Moving Objects ◽  
Multiple Object Tracking ◽  
Tracking Performance ◽  
Displacement Effect ◽  
Inhibitory Processes ◽  
Multiple Object ◽  
Displacement Angle

Human observers are able to keep track of several independently moving objects among other objects. Within theories of multiple object tracking (MOT), distractors are assumed to influence tracking performance only by their distance toward the next target. In order to test this assumption, we designed a variant of the MOT paradigm that involved spatially arranged target-distractor pairs and sudden displacements of distractors during a brief flash. Critically, these displacements maintained target-distractor spacing. Our results show that displacing distractors hurts tracking performance (Experiment 1). Importantly, target-distractor confusions occur within target-distractor pairs with displaced distractors (Experiment 2). This displacement effect increases with an increasing displacement angle (Experiment 3) but is equal at different distances between target and distractor (Experiment 4). This finding illustrates that distractors influence tracking performance beyond pure interobject spacing. We discuss how inhibitory processes as well as relations between targets and distractors might interfere with target tracking.

scholarly journals A Two-Stage Data Association Approach for 3D Multi-Object Tracking

Sensors ◽  
2021 ◽  
Vol 21 (9) ◽  
pp. 2894
Author(s):  
Minh-Quan Dao ◽  
Vincent Frémont
Keyword(s):  
Object Detection ◽  
Object Tracking ◽  
Moving Objects ◽  
Data Association ◽  
Autonomous Driving ◽  
Tracking Accuracy ◽  
Two Stage ◽  
Bipartite Matching ◽  
3D Object ◽  
3D Object Detection

Multi-Object Tracking (MOT) is an integral part of any autonomous driving pipelines because it produces trajectories of other moving objects in the scene and predicts their future motion. Thanks to the recent advances in 3D object detection enabled by deep learning, track-by-detection has become the dominant paradigm in 3D MOT. In this paradigm, a MOT system is essentially made of an object detector and a data association algorithm which establishes track-to-detection correspondence. While 3D object detection has been actively researched, association algorithms for 3D MOT has settled at bipartite matching formulated as a Linear Assignment Problem (LAP) and solved by the Hungarian algorithm. In this paper, we adapt a two-stage data association method which was successfully applied to image-based tracking to the 3D setting, thus providing an alternative for data association for 3D MOT. Our method outperforms the baseline using one-stage bipartite matching for data association by achieving 0.587 Average Multi-Object Tracking Accuracy (AMOTA) in NuScenes validation set and 0.365 AMOTA (at level 2) in Waymo test set.

Tracking Multiple Objects Is Limited Only by Object Spacing, Not by Speed, Time, or Capacity

2010 ◽  
Vol 21 (7) ◽  
pp. 920-925 ◽  
Author(s):  
S.L. Franconeri ◽  
S.V. Jonathan ◽  
J.M. Scimeca
Keyword(s):  
Object Tracking ◽  
Moving Objects ◽  
Multiple Object Tracking ◽  
Single Object ◽  
Multiple Objects ◽  
Performance Constraints ◽  
Root Cause ◽  
Multiple Object ◽  
Tracking Time ◽  
Environment Performance

In dealing with a dynamic world, people have the ability to maintain selective attention on a subset of moving objects in the environment. Performance in such multiple-object tracking is limited by three primary factors—the number of objects that one can track, the speed at which one can track them, and how close together they can be. We argue that this last limit, of object spacing, is the root cause of all performance constraints in multiple-object tracking. In two experiments, we found that as long as the distribution of object spacing is held constant, tracking performance is unaffected by large changes in object speed and tracking time. These results suggest that barring object-spacing constraints, people could reliably track an unlimited number of objects as fast as they could track a single object.

scholarly journals Multiple-Object-Tracking Algorithm Based on Dense Trajectory Voting in Aerial Videos

2019 ◽  
Vol 11 (19) ◽  
pp. 2278
Author(s):  
Tao Yang ◽  
Dongdong Li ◽  
Yi Bai ◽  
Fangbing Zhang ◽  
Sen Li ◽  
...  
Keyword(s):  
Optical Flow ◽  
Object Tracking ◽  
Target Tracking ◽  
Multiple Object Tracking ◽  
Tracking Algorithm ◽  
Frame Rate ◽  
Dense Optical Flow ◽  
Multiple Object ◽  
Dense Trajectory ◽  
Low Frame Rate

In recent years, UAV technology has developed rapidly. Due to the mobility, low cost, and variable monitoring altitude of UAVs, multiple-object detection and tracking in aerial videos has become a research hotspot in the field of computer vision. However, due to camera motion, small target size, target adhesion, and unpredictable target motion, it is still difficult to detect and track targets of interest in aerial videos, especially in the case of a low frame rate where the target position changes too much. In this paper, we propose a multiple-object-tracking algorithm based on dense-trajectory voting in aerial videos. The method models the multiple-target-tracking problem as a voting problem of the dense-optical-flow trajectory to the target ID, which can be applied to aerial-surveillance scenes and is robust to low-frame-rate videos. More specifically, we first built an aerial video dataset for vehicle targets, including a training dataset and a diverse test dataset. Based on this, we trained the neural network model by using a deep-learning method to detect vehicles in aerial videos. Thereafter, we calculated the dense optical flow in adjacent frames, and generated effective dense-optical-flow trajectories in each detection bounding box at the current time. When target IDs of optical-flow trajectories are known, the voting results of the optical-flow trajectories in each detection bounding box are counted. Finally, similarity between detection objects in adjacent frames was measured based on the voting results, and tracking results were obtained by data association. In order to evaluate the performance of this algorithm, we conducted experiments on self-built test datasets. A large number of experimental results showed that the proposed algorithm could obtain good target-tracking results in various complex scenarios, and performance was still robust at a low frame rate by changing the video frame rate. In addition, we carried out qualitative and quantitative comparison experiments between the algorithm and three state-of-the-art tracking algorithms, which further proved that this algorithm could not only obtain good tracking results in aerial videos with a normal frame rate, but also had excellent performance under low-frame-rate conditions.

Data association in multiple object tracking: A survey of recent techniques

2021 ◽  
pp. 116300
Author(s):  
Lionel Rakai ◽  
Huansheng Song ◽  
Shijie Sun ◽  
Wentao Zhang ◽  
Yanni Yang
Keyword(s):  
Object Tracking ◽  
Data Association ◽  
Multiple Object Tracking ◽  
Multiple Object
Sign in / Sign up

Export Citation Format

Share Document