Online multi-person tracking using Integral Channel Features

Kieritz, Hilke; Becker, Stefan; Hübner, Wolfgang; Arens, Michael

doi:10.1109/avss.2016.7738059

Cited by 85 publications

(48 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The GRU is parameterized by matrices W z , W r and W with dimension d×N and matrices U z , U r and U with dimension d × d. z t in Equation (8) is regarded as the update gate, which decides the degree of update the GRU performs. r t in Equation (9) is called the reset gate, which decides how much information from the previous time step should be forgotten.h t in Equation (10) is known as the candidate activation, which is used to compute the new hidden state in Equation (11). In training, the parameters of the GRU are learned in order to update its hidden state in an appropriate way.…”

Section: Recurrent Autoregressive Networkmentioning

confidence: 99%

Recurrent Autoregressive Networks for Online Multi-object Tracking

Fang

Xiang

et al. 2018

2018 IEEE Winter Conference on Applications of Computer Vision (WACV)

243

110

View full text Add to dashboard Cite

The main challenge of online multi-object tracking is to reliably associate object trajectories with detections in each video frame based on their tracking history. In this work, we propose the Recurrent Autoregressive Network (RAN), a temporal generative modeling framework to characterize the appearance and motion dynamics of multiple objects over time. The RAN couples an external memory and an internal memory. The external memory explicitly stores previous inputs of each trajectory in a time window, while the internal memory learns to summarize long-term tracking history and associate detections by processing the external memory. We conduct experiments on the MOT 2015 and 2016 datasets to demonstrate the robustness of our tracking method in highly crowded and occluded scenes. Our method achieves top-ranked results on the two benchmarks. Recurrent CellRecurrent Cell

show abstract

Section: Recurrent Autoregressive Networkmentioning

confidence: 99%

Recurrent Autoregressive Networks for Online Multi-object Tracking

Fang

Xiang

et al. 2018

2018 IEEE Winter Conference on Applications of Computer Vision (WACV)

243

110

View full text Add to dashboard Cite

show abstract

“…We compare our INARLA tracker with nine recent online MPT methods that published their results on the 2D MOT 2015 benchmark, including TSDA OAL [43], RNN LSTM [31], OMT DFH [44], EAMTTpub [45], oICF [46], SCEA [24], MDP [30], DCCRF [47] and AM [48]. Among them, RNN LSTM, DCCRF and AM are deep learning-based methods.…”

Section: Benchmark Evaluationmentioning

confidence: 99%

Instance-aware representation learning and association for online multi-person tracking

Wang

et al. 2019

Pattern Recognition

View full text Add to dashboard Cite

Multi-Person Tracking (MPT) is often addressed within the detection-to-association paradigm. In such approaches, human detections are first extracted in every frame and person trajectories are then recovered by a procedure of data association (usually offline). However, their performances usually degenerate in presence of detection errors, mutual interactions and occlusions. In this paper, we present a deep learning based MPT approach that learns instance-aware representations of tracked persons and robustly online infers states of the tracked persons. Specifically, we design a multibranch neural network (MBN), which predicts the classification confidences and locations of all targets by taking a batch of candidate regions as input. In our MBN architecture, each branch (instance-subnet) corresponds to an individual to be tracked and new branches can be dynamically created for handling newly appearing persons. Then based on the output of MBN, we construct a joint association matrix that represents meaningful states of tracked persons (e.g., being tracked or disappearing from the scene) and solve it by using the efficient Hungarian algorithm. Moreover, we allow the instance-subnets to be updated during tracking by online mining hard examples, accounting to person appearance variations over time. We comprehensively evaluate our framework on a popular MPT benchmark, demonstrating its excellent performance in comparison with recent online MPT methods.

show abstract

“…Before calculating the appearance affinity, we create shape and motion affinity matrices using Eq. 2: 7) where N is the total number of object(X) or observation(Z). Then, we calculate the final affinity matrix as:…”

Section: Gating Techniquementioning

confidence: 99%

“…There have been many works [2,1,7,10,8] which tried to derive accurate appearance affinity. Several works [2,7] tried to design appearance model without using deep neural network(DNN). Those trackers achieved better performance but couldn't significantly improve the performance.…”

Section: Introductionmentioning

confidence: 99%

Online Multi-Object Tracking with Historical Appearance Matching and Scene Adaptive Detection Filtering

Yoon

Boragule

Song

et al. 2018

2018 15th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)

View full text Add to dashboard Cite

In this paper, we propose the methods to handle temporal errors during multi-object tracking. Temporal error occurs when objects are occluded or noisy detections appear near the object. In those situations, tracking may fail and various errors like drift or ID-switching occur. It is hard to overcome temporal errors only by using motion and shape information. So, we propose the historical appearance matching method and joint-input siamese network which was trained by 2-step process. It can prevent tracking failures although objects are temporally occluded or last matching information is unreliable. We also provide useful technique to remove noisy detections effectively according to scene condition. Tracking performance, especially identity consistency, is highly improved by attaching our methods.

show abstract

Online multi-person tracking using Integral Channel Features

Cited by 85 publications

References 18 publications

Recurrent Autoregressive Networks for Online Multi-object Tracking

Recurrent Autoregressive Networks for Online Multi-object Tracking

Instance-aware representation learning and association for online multi-person tracking

Online Multi-Object Tracking with Historical Appearance Matching and Scene Adaptive Detection Filtering

Contact Info

Product

Resources

About