Hehua Liu

Bio: Hehua Liu is an academic researcher from Changsha University of Science and Technology. The author has contributed to research in topics: Artificial intelligence & Computer vision. The author has an hindex of 2, co-authored 2 publications receiving 34 citations.

Learning Local–Global Multiple Correlation Filters for Robust Visual Tracking with Kalman Filter Redetection

Abstract: Visual object tracking is a significant technology for camera-based sensor networks applications Multilayer convolutional features comprehensively used in correlation filter (CF)-based tracking algorithms have achieved excellent performance However, there are tracking failures in some challenging situations because ordinary features are not able to well represent the object appearance variations and the correlation filters are updated irrationally In this paper, we propose a local–global multiple correlation filters (LGCF) tracking algorithm for edge computing systems capturing moving targets, such as vehicles and pedestrians First, we construct a global correlation filter model with deep convolutional features, and choose horizontal or vertical division according to the aspect ratio to build two local filters with hand-crafted features Then, we propose a local–global collaborative strategy to exchange information between local and global correlation filters This strategy can avoid the wrong learning of the object appearance model Finally, we propose a time-space peak to sidelobe ratio (TSPSR) to evaluate the stability of the current CF When the estimated results of the current CF are not reliable, the Kalman filter redetection (KFR) model would be enabled to recapture the object The experimental results show that our presented algorithm achieves better performances on OTB-2013 and OTB-2015 compared with the other latest 12 tracking algorithms Moreover, our algorithm handles various challenges in object tracking well

Distractor-aware visual tracking using hierarchical correlation filters adaptive selection

Abstract: In recent years, the ensembled trackers composed of multi-level features from the pre-trained Convolutional Neural Network (CNN) have achieved top performance in visual tracking. However, due to the background clutters and the distractors in the search area, the tracker tends to drift towards an area that is similar to the target. In order to suppress interference of background and similar objects, we propose an effective Distractor-Aware Map (DAM), which can reduce the weights of the interference area in the multi-level features. Thus, the tracker can focus on the target to greatly eliminate the risk of drift. In addition, we build a Hierarchical Correlation Filters Model (HCFM) based on the multi-level convolutional features to track targets in parallel. To further improve the robustness of tracking, a novel Multi-Model Adaptive Selection (MAS) mechanism is presented. This mechanism can evaluate the confidence of the response map in HCFM to adaptively select the most reliable model. Finally, in order to appropriately update the model to adapt to appearance changes of the target, we propose an adaptive updating strategy for the updates of the DAM and HCFM. We perform comprehensive experiments on OTB-2013, OTB-2015 and Temple Color datasets and the experimental results show the superiority of our algorithm over other state-of-the-art approaches.

Adaptive response maps fusion of correlation filters with anti-occlusion mechanism for visual object tracking

Abstract: Abstract Despite the impressive performance of correlation filter-based trackers in terms of robustness and accuracy, the trackers have room for improvement. The majority of existing trackers use a single feature or fixed fusion weights, which makes it possible for tracking to fail in the case of deformation or severe occlusion. In this paper, we propose a multi-feature response map adaptive fusion strategy based on the consistency of individual features and fused feature. It is able to improve the robustness and accuracy by building the better object appearance model. Moreover, since the response map has multiple local peaks when the target is occluded, we propose an anti-occlusion mechanism. Specifically, if the nonmaximal local peak is satisfied with our proposed conditions, we generate a new response map which is obtained by moving the center of the region of interest to the nonmaximal local peak position of the response map and re-extracting features. We then select the response map with the largest response value as the final response map. This proposed anti-occlusion mechanism can effectively cope with the problem of tracking failure caused by occlusion. Finally, by adjusting the learning rate in different scenes, we designed a high-confidence model update strategy to deal with the problem of model pollution. Besides, we conducted experiments on OTB2013, OTB2015, TC128 and UAV123 datasets and compared them with the current state-of-the-art algorithms, and the proposed algorithms have impressive advantages in terms of accuracy and robustness.

Adaptive response maps fusion of correlation filters with anti-occlusion mechanism for visual object tracking

Abstract: Abstract Despite the impressive performance of correlation filter-based trackers in terms of robustness and accuracy, the trackers have room for improvement. The majority of existing trackers use a single feature or fixed fusion weights, which makes it possible for tracking to fail in the case of deformation or severe occlusion. In this paper, we propose a multi-feature response map adaptive fusion strategy based on the consistency of individual features and fused feature. It is able to improve the robustness and accuracy by building the better object appearance model. Moreover, since the response map has multiple local peaks when the target is occluded, we propose an anti-occlusion mechanism. Specifically, if the nonmaximal local peak is satisfied with our proposed conditions, we generate a new response map which is obtained by moving the center of the region of interest to the nonmaximal local peak position of the response map and re-extracting features. We then select the response map with the largest response value as the final response map. This proposed anti-occlusion mechanism can effectively cope with the problem of tracking failure caused by occlusion. Finally, by adjusting the learning rate in different scenes, we designed a high-confidence model update strategy to deal with the problem of model pollution. Besides, we conducted experiments on OTB2013, OTB2015, TC128 and UAV123 datasets and compared them with the current state-of-the-art algorithms, and the proposed algorithms have impressive advantages in terms of accuracy and robustness.

AGTH-Net: Attention-Based Graph Convolution-Guided Third-Order Hourglass Network for Sports Video Classification.

Abstract: As a hot research topic, sports video classification research has a wide range of applications in switched TV, video on demand, smart TV, and other fields and is closely related to people’s lives. Under this background, sports video classification research has aroused great interest in people. However, the existing methods usually use manual video classification, which the workers themselves often influence. It is challenging to ensure the accuracy of the results, leading to the wrong classification. Due to these limitations, we introduce neural network technology to the automatic classification of sports. This paper proposed a novel attention-based graph convolution-guided third-order hourglass network (AGTH-Net) classification model. First, we designed a kind of figure convolution model based on the attention mechanism. The model is the key to introduce the attention mechanism for neighborhood node weights’ allocation. It reduces the impact of error nodes in the neighborhood while avoiding manual weight assignment. Second, according to the sports complex video image characteristics, we use the third-order hourglass network structure. It is used for the extraction and fusion of multiscale characteristics of sports. In addition, in the hourglass, internal network residual-intensive modules are introduced, realizing characteristics in different levels of network transfer and reuse. It is helpful for maximum details to feature extracting and enhancing the network expression ability. Comparison and ablation experiments are also carried out to prove the effectiveness and superiority of the proposed algorithm.

Siamese anchor-free object tracking with multiscale spatial attentions.

Abstract: Recently, object trackers based on Siamese networks have attracted considerable attentions due to their remarkable tracking performance and widespread application. Especially, the anchor-based methods exploit the region proposal subnetwork to get accurate prediction of a target and make great performance improvement. However, those trackers cannot capture the spatial information very well and the pre-defined anchors will hinder robustness. To solve these problems, we propose a Siamese-based anchor-free object tracking algorithm with multiscale spatial attentions in this paper. Firstly, we take ResNet-50 as the backbone network to generate multiscale features of both template patch and search regions. Secondly, we propose the spatial attention extraction (SAE) block to capture the spatial information among all positions in the template and search region feature maps. Thirdly, we put these features into the SAE block to get the multiscale spatial attentions. Finally, an anchor-free classification and regression subnetwork is used for predicting the location of the target. Unlike anchor-based methods, our tracker directly predicts the target position without predefined parameters. Extensive experiments with state-of-the-art trackers are carried out on four challenging visual object tracking benchmarks: OTB100, UAV123, VOT2016 and GOT-10k. Those experimental results confirm the effectiveness of our proposed tracker.

Influencing Factors of Microlecture on the Teaching Effect of Ideological and Political Courses in Colleges

Abstract: Microlecture has the characteristics of single topic, easy to learn, convenient sharing, and real-time interaction. Whether these characteristics are conducive to enhancing the effect of ideological and political teaching in colleges is the focus of this paper. We have constructed the influence factor model of microlecture on ideological and political teaching effect in colleges. Through questionnaire survey and empirical analysis, we verify the four characteristics of microlecture. The results show that in microlecture teaching, single topic, easy to learn, and sharing convenience are the main factors to enhance the teaching effect of ideological and political course in colleges, while real-time interaction had no significant effect. Our study has enriched the literature of microlecture in ideological and political teaching and confirmed that microlecture can improve the teaching effect of ideological and political courses in colleges. Based on the research results, we propose the following recommendations: (1) in ideological and political teaching, recorded microlecture should concentrate on a single topic as far as possible, and the time of microlecture should be controlled to be shorter; (2) since students believe that microlecture make their study easier and share convenience, universities should consider promoting this mode in ideological and political teaching.