Robust occlusion-aware part-based visual tracking with object scale adaptation

Wang, Xin; Hou, Zhiqiang; Yu, Wei; Pu, Lei; Jin, Zhou; Qin, Xianxiang

doi:10.1016/j.patcog.2018.04.011

Cited by 34 publications

(10 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed LSDCFc tracker outperforms the baseline tracker SRDCF and its two variants in precision and achieves a comparable performance in success rate. Meanwhile, our tracker LSDCFc gains of 4.2% in precision and 2.1% in success rate compared to the recent part-based tracker OAPT [66]. Overall, our proposed tracker achieves competitive results against the state-of-the-art trackers on the Temple-Color-128 benchmark.…”

Section: E Performance Evaluation On Tc128 Benchmarkmentioning

confidence: 85%

Learning Local Structured Correlation Filters for Visual Tracking via Spatial Joint Regularization

2019

View full text Add to dashboard Cite

Robust visual tracking is a fundamental problem in the field of computer vision and has a wide range of practical applications. Recent progress in developing robust tracking methods are mainly made upon discriminative correlation filters (DCF). However, most DCF-based methods develop their trackers under the assumption of a holistic appearance model, ignoring the underlying spatial local structural information. In this paper, we introduce the tree-structured group sparsity regularization into the DCF-based formula. The correlation filter to be learned is divided into hierarchical local groups. The relationship between the response and the circularly shifted target appearance is regularized by applying the l 1 -norm across the l 2norm of the hierarchical local filter groups. Moreover, a local response consistency term is incorporated together with the structured sparsity to make each local filter group contributes equally to the final response. The accelerated proximal gradient method is employed to optimize this non-smooth composite regularization problem. Benefiting from the properties of circulant matrices, several key steps in the optimization process can be efficiently solved in the frequency domain. The experiments are conducted on four publicly available visual tracking benchmarks. Both quantitative and qualitative evaluations demonstrate that the proposed tracking method performs favorably against a number of state-of-the-art tracking methods.

show abstract

Section: E Performance Evaluation On Tc128 Benchmarkmentioning

confidence: 85%

Learning Local Structured Correlation Filters for Visual Tracking via Spatial Joint Regularization

2019

View full text Add to dashboard Cite

show abstract

“…Occlusion is currently a problem that needs to be solved urgently in object detection, because after the object is occluded, its feature information will be greatly reduced, and this will have an effect on the occluded object, making it extremely difficult to detect and easy to be misrecognized [ 44 ]. In view of this situation, this paper proposes a feature extraction model based on contextual information.…”

Section: Sc-faster R-cnnmentioning

confidence: 99%

Object Detection Based on Faster R-CNN Algorithm with Skip Pooling and Fusion of Contextual Information

Xiao

Wang

Zhang

et al. 2020

Sensors

View full text Add to dashboard Cite

Deep learning is currently the mainstream method of object detection. Faster region-based convolutional neural network (Faster R-CNN) has a pivotal position in deep learning. It has impressive detection effects in ordinary scenes. However, under special conditions, there can still be unsatisfactory detection performance, such as the object having problems like occlusion, deformation, or small size. This paper proposes a novel and improved algorithm based on the Faster R-CNN framework combined with the Faster R-CNN algorithm with skip pooling and fusion of contextual information. This algorithm can improve the detection performance under special conditions on the basis of Faster R-CNN. The improvement mainly has three parts: The first part adds a context information feature extraction model after the conv5_3 of the convolutional layer; the second part adds skip pooling so that the former can fully obtain the contextual information of the object, especially for situations where the object is occluded and deformed; and the third part replaces the region proposal network (RPN) with a more efficient guided anchor RPN (GA-RPN), which can maintain the recall rate while improving the detection performance. The latter can obtain more detailed information from different feature layers of the deep neural network algorithm, and is especially aimed at scenes with small objects. Compared with Faster R-CNN, you only look once series (such as: YOLOv3), single shot detector (such as: SSD512), and other object detection algorithms, the algorithm proposed in this paper has an average improvement of 6.857% on the mean average precision (mAP) evaluation index while maintaining a certain recall rate. This strongly proves that the proposed method has higher detection rate and detection efficiency in this case.

show abstract

“…[22] took advantage of depth‐layer information for occlusion detection, they used the information of time and space to distinguish occlusion. In [23], Wang et al . proposed an occlusion‐aware model on correlation filters to make full use of the global model and part‐based model for occlusion detection.…”

Section: Related Workmentioning

confidence: 99%