Instance flow based online multiple object tracking

Bullinger, Sebastian; Bodensteiner, Christoph; Arens, Michael

doi:10.1109/icip.2017.8296388

Cited by 19 publications

(31 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this way, only a few objects would have to be analyzed by the CNN, making the detection step faster. [76], where instead of computing classical bounding boxes in the detection step, a Multi-task Network Cascade [77] was instead employed to obtain instance-aware semantic segmentation maps. The authors argue that since the 2D shape of instances, differently from rectangular bounding boxes, do not contain background structures or parts of other objects, optical flow based tracking algorithms would perform better, especially when the target position in the image is also subject to camera motion in addition to the object's own motion.…”

Section: Other Uses Of Cnns In the Detection Stepmentioning

confidence: 99%

Deep learning in video multi-object tracking: A survey

et al. 2020

View full text Add to dashboard Cite

The problem of Multiple Object Tracking (MOT) consists in following the trajectory of different objects in a sequence, usually a video. In recent years, with the rise of Deep Learning, the algorithms that provide a solution to this problem have benefited from the representational power of deep models. This paper provides a comprehensive survey on works that employ Deep Learning models to solve the task of MOT on single-camera videos. Four main steps in MOT algorithms are identified, and an in-depth review of how Deep Learning was employed in each one of these stages is presented. A complete experimental comparison of the presented works on the three MOTChallenge datasets is also provided, identifying a number of similarities among the top-performing methods and presenting some possible future research directions.In this section, a general description about the problem of MOT is provided. The main characteristics and common steps of MOT algorithms are identified and described in section 2.1. The metrics that are usually employed to evaluate the performance of the models are discussed in section 2.2, while the most important benchmark datasets are presented in section 2.3. 7 The website says the detections were obtained using a model based on a latent SVM, or L-SVM. That model is now known as Deformable Parts Model (DPM). 8

show abstract

Section: Other Uses Of Cnns In the Detection Stepmentioning

confidence: 99%

Deep learning in video multi-object tracking: A survey

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Choi [17] proposed the aggregated local flow descriptor that can accurately measure the affinity between a pair of detections. Bullinger et alproposed a method that exploits instance segmentation and predicts position and shape in the next frame by optical flows [18]. However, these methods require a lot of running time because they perform human detection in every frame and combine the detection result with optical flow.…”

Section: Tracking Based On Detection and Optical Flowmentioning

confidence: 99%

“…The optical flow can also obtain detection results even in situations where the human detector misses someone. Many tracking methods using optical flow have been proposed [14,15,16,17,18], and they aim to improve the tracking accuracy by human detection and optical flow at every frame. In contrast, we aim to maintain the tracking accuracy just with optical flow with the support of skipped detections.…”

Section: Introductionmentioning

confidence: 99%

SDOF-Tracker: Fast and Accurate Multiple Human Tracking by Skipped-Detection and Optical-Flow

Nishimura¹,

Komorita²,

Kawanishi³

et al. 2021

Preprint

View full text Add to dashboard Cite

Multiple human tracking is a fundamental problem for scene understanding. Although both accuracy and speed are required in real-world applications, recent tracking methods based on deep learning have focused on accuracy and require substantial running time. This study aims to improve running speed by performing human detection at a certain frame interval because it accounts for most of the running time. The question is how to maintain accuracy while skipping human detection. In this paper, we propose a method that complements the detection results with optical flow, based on the fact that someone's appearance does not change much between adjacent frames. To maintain the tracking accuracy, we introduce robust interest point selection within human regions and a tracking termination metric calculated by the distribution of the interest points. On the MOT20 dataset in the MOTChallenge, the proposed SDOF-Tracker achieved the best performance in terms of the total running speed while maintaining the MOTA metric. Our code is available at https: //anonymous.4open.science/r/sdof-tracker-75AE.This study aims to resolve the speed-accuracy trade-off problem by bypassing every-frame human detection, which is a computationally heavy task, that is, we perform it at a certain interval. During the interval, human detection is skipped. We named this process Skipped-Detection. The question here is how to complement human detection in skipped frames.

show abstract

“…(1) We present a new framework to reconstruct the threedimensional trajectory of moving instances of known object categories in monocular video data leveraging sateof-the-art semantic segmentation and structure from motion approaches. (2) We propose a novel method to compute object motion trajectories consistent to image observations and background structures. (3) In contrast to previous work, we quantitatively evaluate the reconstructed object motion trajectories.…”

Section: Contributionmentioning

confidence: 99%

“…We track twodimensional object shapes on pixel level across video sequences following the approach presented in [2]. In contrast to [2], we identify object shapes exploiting the instanceaware semantic segmentation method presented in [14] and associate extracted object shapes of subsequent frames using the optical flow approach described in [10]. Without the loss of generality, we describe motion trajectory reconstructions of single objects.…”

Section: Object Motion Trajectory Reconstructionmentioning

confidence: 99%

3D Trajectory Reconstruction of Dynamic Objects Using Planarity Constraints

Bullinger¹,

Bodensteiner²,

Arens³

et al. 2017

Preprint

Self Cite

View full text Add to dashboard Cite

We present a method to reconstruct the threedimensional trajectory of a moving instance of a known object category in monocular video data. We track the two-dimensional shape of objects on pixel level exploiting instance-aware semantic segmentation techniques and optical flow cues. We apply Structure from Motion techniques to object and background images to determine for each frame camera poses relative to object instances and background structures. By combining object and background camera pose information, we restrict the object trajectory to a one-parameter family of possible solutions. We compute a ground representation by fusing background structures and corresponding semantic segmentations. This allows us to determine an object trajectory consistent to image observations and reconstructed environment model. Our method is robust to occlusion and handles temporarily stationary objects. We show qualitative results using drone imagery. Due to the lack of suitable benchmark datasets we present a new dataset to evaluate the quality of reconstructed threedimensional object trajectories. The video sequences contain vehicles in urban areas and are rendered using the path-tracing render engine Cycles to achieve realistic results. We perform a quantitative evaluation of the presented approach using this dataset. Our algorithm achieves an average reconstruction-to-ground-truth distance of 0.31 meter. The dataset will be publicly available on our website 1 .

show abstract

Instance flow based online multiple object tracking

Cited by 19 publications

References 16 publications

Deep learning in video multi-object tracking: A survey

Deep learning in video multi-object tracking: A survey

SDOF-Tracker: Fast and Accurate Multiple Human Tracking by Skipped-Detection and Optical-Flow

3D Trajectory Reconstruction of Dynamic Objects Using Planarity Constraints

Contact Info

Product

Resources

About