Pedestrian trajectory prediction is a crucial task for many domains, such as self-driving, navigation robots and video surveillance. The performance of trajectory prediction can be improved in various patterns, including using a more effective network, considering more complicated social interactions, and utilizing sufficient information. On the one hand, the change of subsequent trajectory depends on the geographical scene and the social interaction with other pedestrians in the same scene. On the other hand, the subsequent trajectory also makes some real-time adjustments according to the judgment of pedestrian behavior. Therefore, we propose a novel behavior recognition module to obtain extra pedestrian behavior information. To guarantee the precision and diversity of prediction, this paper builds the Geographical, the Social and the Behavior feature modules based on the GAN framework to process information. As a result, we present a trajectory prediction approach, referred to as the BR-GAN, which exploits geographical, social and behavior context-aware. The BR-GAN achieves greater accuracy in parts of the ETH/UCY datasets compared with some baselines. We will republic all of them onhttps://github.com/HITjian/Pedestrian-trajectoty-prediction-based-on-behavior-recognition.

Recent advances in robust principle component analysis offers a powerful method for solving a wide variety of low-level vision problems. However, if the input data is very large, especially when high-resolution images are involved, it makes RPCA computationally prohibitive for many real applications. To tackle this problem, we propose a fixed-rank RPCA method that uses coupled dictionaries (FRPCA-CD) to handle high-resolution images. FRPCA-CD downsamples high-resolution images into low-resolution images, performs FRPCA on the low-level images to obtain the low-rank matrix, which is reconstructed at original resolution by coupled dictionaries. Comprehensive tests performed on video background recovery, noise reduction in photometric stereo, and image reflection removal problems show that FRPCA-CD can reduce computation time and memory space drastically without sacrificing accuracy.

Face images are very important in human social activities, which can be severely hampered when they are corrupted by occluders such as eyeglasses, face marks, and scarfs. Existing methods for removing occlusions in face images can be grouped into three broad categories, namely PCA, robust PCA (RPCA), and sparse coding. The major weaknesses of these methods are inconsistent performance across test conditions and possible corruption of unoccluded part of the recovered target image. This paper presents variable-threshold RPCA (VRPCA) method based on RPCA with variable thresholding. Comprehensive tests show that VRPCA is able to preserve the unoccluded parts of the target image with practically zero error. Compared to existing methods, it is more accurate, reliable, and consistent across various test conditions.

Sparse representation has shown its merits in solving some classification problems and delivered some impressive results in face recognition. However, the unsupervised optimization of the sparse representation may result in undesired classification outcome if the variations of the data population are not well represented by the training samples. In this paper, a method of class-wise sparse representation (CSR) is proposed to tackle the problems of the conventional sample-wise sparse representation and applied to face recognition. It seeks an optimum representation of the query image by minimizing the class-wise sparsity of the training data. To tackle the problem of the uncontrolled training data, this paper further proposes a collaborative patch (CP) framework, together with the proposed CSR, named CSR-CP. Different from the conventional patch-based methods that optimize each patch representation separately, the CSR-CP approach optimizes all patches together to seek a CP groupwise sparse representation by putting all patches of an image into a group. It alleviates the problem of losing discriminative information in the training data caused by the partition of the image into patches. Extensive experiments on several benchmark face databases demonstrate that the proposed CSR-CP significantly outperforms the sparse representation-related holistic and patch-based approaches.

Sparse representation provides an effective tool for classification under the conditions that every class has sufficient representative training samples and the training data are uncorrupted. These conditions may not hold true in many practical applications. Face identification is an example where we have a large number of identities but sufficient representative and uncorrupted training images cannot be guaranteed for every identity. A violation of the two conditions leads to a poor performance of the sparse representation-based classification (SRC). This paper addresses this critic issue by analyzing the merits and limitations of SRC. A sparse- and dense-hybrid representation (SDR) framework is proposed in this paper to alleviate the problems of SRC. We further propose a procedure of supervised low-rank (SLR) dictionary decomposition to facilitate the proposed SDR framework. In addition, the problem of the corrupted training data is also alleviated by the proposed SLR dictionary decomposition. The application of the proposed SDR-SLR approach in face recognition verifies its effectiveness and advancement to the field. Extensive experiments on benchmark face databases demonstrate that it consistently outperforms the state-of-the-art sparse representation based approaches and the performance gains are significant in most cases.

In this paper, we address the robust face recognition problem. Recently, trace lasso was introduced as an adaptive norm based on the training data. It uses the correlation among the training samples to tackle the instability problem of sparse representation coding. Trace lasso naturally clusters the highly correlated data together. However, the face images with similar variations, such as illumination or expression, often have higher correlation than those from the same class. In this case, the result of trace lasso is contradictory to the goal of recognition, which is to cluster the samples according to their identities. Therefore, trace lasso is not a good choice for face recognition task. In this work, we propose a supervised trace lasso (STL) framework by employing the class label information. To represent the query sample, the proposed STL approach seeks the sparsity of the number of classes instead of the number of training samples. This directly coincides with the objective of the classification. Furthermore, an efficient algorithm to solve the optimization problem of proposed method is given. The extensive experimental results have demonstrated the effectiveness of the proposed framework.

In this work, we focus on the problem of partially occluded face recognition. Using a robust estimator, we detect and trim the contaminated pixels from query sample. The corresponding pixels in the training samples are trimmed as well. The linear regression is applied to the trimmed images. Finally, the query image is labeled to the class with minimum normalized reconstruction error. Extensive experiments on benchmark face datasets demonstrate that the proposed approach is much more robust than state-of-the-art methods in dealing with occluded faces.

Over the past few years, sparse representation (SR) becomes a hotspot and applied in many research fields. Sparsity preserving projections (SPP) utilizes SR to dimensionality reduction (DR) for face classification. However, as the original framework of SR is unsupervised, SPP can not employ the class information, which is very crucial for classification. To address this problem, we propose an algorithm, namely supervised SR (SSR), to cooperate with label information. Furthermore, we also propose a DR method, discriminative sparsity preserving embedding (DSPE), in this paper. DSPE learns the discriminative sparse structure with SSR and finds the low dimensional subspace that reduces the within class distances and keeps the between class distances. Compared with the related state-of-the-art methods, experimental results on benchmark face databases verify the advancement of the proposed method.

This work proposes a novel framework of robust face recognition based on the sparse representation. Image is first divided into modules and each module is processed separately to determine its reliability. A reconstructed image from the modules weighted by their reliability is formed for the robust recognition. We propose to use the modular sparsity and residual jointly to determine the modular reliability. The proposed framework advances both the modular and global sparse representation approaches, especially in dealing with disguise, large illumination variations and expression changes. Compared with the related state-of-the-art methods, experimental results on benchmark face databases verify the advancement of the proposed method.