Xinbo Zhao

Xinbo Zhao, Yingxue Zhang, Xin Zhang et al.

Enhancing diverse human decision-making processes in an urban environment is a critical issue across various applications, including ride-sharing vehicle dispatching, public transportation management, and autonomous driving. Offline reinforcement learning (RL) is a promising approach to learn and optimize human urban strategies (or policies) from pre-collected human-generated spatial-temporal urban data. However, standard offline RL faces two significant challenges: (1) data scarcity and data heterogeneity, and (2) distributional shift. In this paper, we introduce MODA -- a Multi-Task Offline Reinforcement Learning with Contrastive Data Sharing approach. MODA addresses the challenges of data scarcity and heterogeneity in a multi-task urban setting through Contrastive Data Sharing among tasks. This technique involves extracting latent representations of human behaviors by contrasting positive and negative data pairs. It then shares data presenting similar representations with the target task, facilitating data augmentation for each task. Moreover, MODA develops a novel model-based multi-task offline RL algorithm. This algorithm constructs a robust Markov Decision Process (MDP) by integrating a dynamics model with a Generative Adversarial Network (GAN). Once the robust MDP is established, any online RL or planning algorithm can be applied. Extensive experiments conducted in a real-world multi-task urban setting validate the effectiveness of MODA. The results demonstrate that MODA exhibits significant improvements compared to state-of-the-art baselines, showcasing its capability in advancing urban decision-making processes. We also made our code available to the research community.

Na Li, Xinbo Zhao

Human gait is one of important biometric characteristics for human identification at a distance. In practice, occlusion usually occurs and seriously affects accuracy of gait recognition. However, there is no available database to support in-depth research of this problem, and state-of-arts gait recognition methods have not paid enough attention to it, thus this paper focuses on gait recognition under occlusion. We collect a new gait recognition database called OG RGB+D database, which breaks through the limitation of other gait databases and includes multimodal gait data of various occlusions (self-occlusion, active occlusion, and passive occlusion) by our multiple synchronous Azure Kinect DK sensors data acquisition system (multi-Kinect SDAS) that can be also applied in security situations. Because Azure Kinect DK can simultaneously collect multimodal data to support different types of gait recognition algorithms, especially enables us to effectively obtain camera-centric multi-person 3D poses, and multi-view is better to deal with occlusion than single-view. In particular, the OG RGB+D database provides accurate silhouettes and the optimized human 3D joints data (OJ) by fusing data collected by multi-Kinects which are more accurate in human pose representation under occlusion. We also use the OJ data to train an advanced 3D multi-person pose estimation model to improve its accuracy of pose estimation under occlusion for universality. Besides, as human pose is less sensitive to occlusion than human appearance, we propose a novel gait recognition method SkeletonGait based on human dual skeleton model using a framework of siamese spatio-temporal graph convolutional networks (siamese ST-GCN). The evaluation results demonstrate that SkeletonGait has competitive performance compared with state-of-art gait recognition methods on OG RGB+D database and popular CAISA-B database.

Weiquan Huang, Yan Bai, Qiuyu Ren et al.

Existing public person Re-Identification~(ReID) datasets are small in modern terms because of labeling difficulty. Although unlabeled surveillance video is abundant and relatively easy to obtain, it is unclear how to leverage these footage to learn meaningful ReID representations. In particular, most existing unsupervised and domain adaptation ReID methods utilize only the public datasets in their experiments, with labels removed. In addition, due to small data sizes, these methods usually rely on fine tuning by the unlabeled training data in the testing domain to achieve good performance. Inspired by the recent progress of large-scale self-supervised image classification using contrastive learning, we propose to learn ReID representation from large-scale unlabeled surveillance video alone. Assisted by off-the-shelf pedestrian detection tools, we apply the contrastive loss at both the image and the tracklet levels. Together with a principal component analysis step using camera labels freely available, our evaluation using a large-scale unlabeled dataset shows far superior performance among unsupervised methods that do not use any training data in the testing domain. Furthermore, the accuracy improves with the data size and therefore our method has great potential with even larger and more diversified datasets.

Aiqing Fang, Xinbo Zhao, Jiaqi Yang et al.

The deep-learning-based image restoration and fusion methods have achieved remarkable results. However, the existing restoration and fusion methods paid little research attention to the robustness problem caused by dynamic degradation. In this paper, we propose a novel dynamic image restoration and fusion neural network, termed as DDRF-Net, which is capable of solving two problems, i.e., static restoration and fusion, dynamic degradation. In order to solve the static fusion problem of existing methods, dynamic convolution is introduced to learn dynamic restoration and fusion weights. In addition, a dynamic degradation kernel is proposed to improve the robustness of image restoration and fusion. Our network framework can effectively combine image degradation with image fusion tasks, provide more detailed information for image fusion tasks through image restoration loss, and optimize image restoration tasks through image fusion loss. Therefore, the stumbling blocks of deep learning in image fusion, e.g., static fusion weight and specifically designed network architecture, are greatly mitigated. Extensive experiments show that our method is more superior compared with the state-of-the-art methods.

Aiqing Fang, Xinbo Zhao, Jiaqi Yang et al.

Existing image fusion methods pay few research attention to image fusion efficiency and network architecture. However, the efficiency and accuracy of image fusion has an important impact in practical applications. To solve this problem, we propose an \textit{efficient autonomous evolution image fusion method, dubed by AE-Netv2}. Different from other image fusion methods based on deep learning, AE-Netv2 is inspired by human brain cognitive mechanism. Firstly, we discuss the influence of different network architecture on image fusion quality and fusion efficiency, which provides a reference for the design of image fusion architecture. Secondly, we explore the influence of pooling layer on image fusion task and propose an image fusion method with pooling layer. Finally, we explore the commonness and characteristics of different image fusion tasks, which provides a research basis for further research on the continuous learning characteristics of human brain in the field of image fusion. Comprehensive experiments demonstrate the superiority of AE-Netv2 compared with state-of-the-art methods in different fusion tasks at a real time speed of 100+ FPS on GTX 2070. Among all tested methods based on deep learning, AE-Netv2 has the faster speed, the smaller model size and the better robustness.

Aiqing Fang, Xinbo Zhao, Jiaqi Yang et al.

In order to solve the robustness and generality problems of the image fusion task,inspired by the human brain cognitive mechanism, we propose a robust and general image fusion method with autonomous evolution ability, and is therefore denoted with AE-Net. Through the collaborative optimization of multiple image fusion methods to simulate the cognitive process of human brain, unsupervised learning image fusion task can be transformed into semi-supervised image fusion task or supervised image fusion task, thus promoting the evolutionary ability of network model weight. Firstly, the relationship between human brain cognitive mechanism and image fusion task is analyzed and a physical model is established to simulate human brain cognitive mechanism. Secondly, we analyze existing image fusion methods and image fusion loss functions, select the image fusion method with complementary features to construct the algorithm module, establish the multi-loss joint evaluation function to obtain the optimal solution of algorithm module. The optimal solution of each image is used to guide the weight training of network model. Our image fusion method can effectively unify the cross-modal image fusion task and the same modal image fusion task, and effectively overcome the difference of data distribution between different datasets. Finally, extensive numerical results verify the effectiveness and superiority of our method on a variety of image fusion datasets, including multi-focus dataset, infrared and visi-ble dataset, medical image dataset and multi-exposure dataset. Comprehensive experiments demonstrate the superiority of our image fusion method in robustness and generality. In addition, experimental results also demonstate the effectiveness of human brain cognitive mechanism to improve the robustness and generality of image fusion.

Na Li, Xinbo Zhao, Chong Ma

Gait, as one of unique biometric features, has the advantage of being recognized from a long distance away, can be widely used in public security. Considering 3D pose estimation is more challenging than 2D pose estimation in practice , we research on using 2D joints to recognize gait in this paper, and a new model-based gait recognition method JointsGait is put forward to extract gait information from 2D human body joints. Appearance-based gait recognition algorithms are prevalent before. However, appearance features suffer from external factors which can cause drastic appearance variations, e.g. clothing. Unlike previous approaches, JointsGait firstly extracted spatio-temporal features from 2D joints using gait graph convolutional networks, which are less interfered by external factors. Secondly, Joints Relationship Pyramid Mapping (JRPM) are proposed to map spatio-temporal gait features into a discriminative feature space with biological advantages according to the relationship of human joints when people are walking at various scales. Finally, we design a fusion loss strategy to help the joints features to be insensitive to cross-view. Our method is evaluated on two large datasets, Kinect Gait Biometry Dataset and CASIA-B. On Kinect Gait Biometry Dataset database, JointsGait only uses corresponding 2D coordinates of joints, but achieves satisfactory recognition accuracy compared with those model-based algorithms using 3D joints. On CASIA-B database, the proposed method greatly outperforms advanced model-based methods in all walking conditions, even performs superior to state-of-art appearance-based methods when clothing seriously affect people's appearance. The experimental results demonstrate that JointsGait achieves the state-of-art performance despite the low dimensional feature (2D body joints) and is less affected by the view variations and clothing variation.

Aiqing Fang, Xinbo Zhao, Jiaqi Yang et al.

The human visual perception system has strong robustness in image fusion. This robustness is based on human visual perception system's characteristics of feature selection and non-linear fusion of different features. In order to simulate the human visual perception mechanism in image fusion tasks, we propose a multi-source image fusion framework that combines illuminance factors and attention mechanisms. The framework effectively combines traditional image features and modern deep learning features. First, we perform multi-scale decomposition of multi-source images. Then, the visual saliency map and the deep feature map are combined with the illuminance fusion factor to perform high-low frequency nonlinear fusion. Secondly, the characteristics of high and low frequency fusion are selected through the channel attention network to obtain the final fusion map. By simulating the nonlinear characteristics and selection characteristics of the human visual perception system in image fusion, the fused image is more in line with the human visual perception mechanism. Finally, we validate our fusion framework on public datasets of infrared and visible images, medical images and multi-focus images. The experimental results demonstrate the superiority of our fusion framework over state-of-arts in visual quality, objective fusion metrics and robustness.

Aiqing Fang, Xinbo Zhao, Yanning Zhang

The human visual perception system has very strong robustness and contextual awareness in a variety of image processing tasks. This robustness and the perception ability of contextual awareness is closely related to the characteristics of multi-task auxiliary learning and subjective attention of the human visual perception system. In order to improve the robustness and contextual awareness of image fusion tasks, we proposed a multi-task auxiliary learning image fusion theory guided by subjective attention. The image fusion theory effectively unifies the subjective task intention and prior knowledge of human brain. In order to achieve our proposed image fusion theory, we first analyze the mechanism of multi-task auxiliary learning, build a multi-task auxiliary learning network. Secondly, based on the human visual attention perception mechanism, we introduce the human visual attention network guided by subjective tasks on the basis of the multi-task auxiliary learning network. The subjective intention is introduced by the subjective attention task model, so that the network can fuse images according to the subjective intention. Finally, in order to verify the superiority of our image fusion theory, we carried out experiments on the combined vision system image data set, and the infrared and visible image data set for experimental verification. The experimental results demonstrate the superiority of our fusion theory over state-of-arts in contextual awareness and robustness.

Aiqing Fang, Xinbo Zhao, Jiaqi Yang et al.

The characteristics of feature selection, nonlinear combination and multi-task auxiliary learning mechanism of the human visual perception system play an important role in real-world scenarios, but the research of image fusion theory based on the characteristics of human visual perception is less. Inspired by the characteristics of human visual perception, we propose a robust multi-task auxiliary learning optimization image fusion theory. Firstly, we combine channel attention model with nonlinear convolutional neural network to select features and fuse nonlinear features. Then, we analyze the impact of the existing image fusion loss on the image fusion quality, and establish the multi-loss function model of unsupervised learning network. Secondly, aiming at the multi-task auxiliary learning mechanism of human visual perception system, we study the influence of multi-task auxiliary learning mechanism on image fusion task on the basis of single task multi-loss network model. By simulating the three characteristics of human visual perception system, the fused image is more consistent with the mechanism of human brain image fusion. Finally, in order to verify the superiority of our algorithm, we carried out experiments on the combined vision system image data set, and extended our algorithm to the infrared and visible image and the multi-focus image public data set for experimental verification. The experimental results demonstrate the superiority of our fusion theory over state-of-arts in generality and robustness.