Human Pose Variations Research Articles

Analysis and best parameters selection for person recognition based on gait model using CNN algorithm and image augmentation

Person Recognition based on Gait Model (PRGM) and motion features is are indeed a challenging and novel task due to their usages and to the critical issues of human pose variation, human body occlusion, camera view variation, etc. In this project, a deep convolution neural network (CNN) was modified and adapted for person recognition with Image Augmentation (IA) technique depending on gait features. Adaptation aims to get best values for CNN parameters to get best CNN model. In Addition to the CNN parameters Adaptation, the design of CNN model itself was adapted to get best model structure; Adaptation in the design was affected the type, the number of layers in CNN and normalization between them. After choosing best parameters and best design, Image augmentation was used to increase the size of train dataset with many copies of the image to boost the number of different images that will be used to train Deep learning algorithms. The tests were achieved using known dataset (Market dataset). The dataset contains sequential pictures of people in different gait status. The image in CNN model as matrix is extracted to many images or matrices by the convolution, so dataset size may be bigger by hundred times to make the problem a big data issue. In this project, results show that adaptation has improved the accuracy of person recognition using gait model comparing to model without adaptation. In addition, dataset contains images of person carrying things. IA technique improved the model to be robust to some variations such as image dimensions (quality and resolution), rotations and carried things by persons. Results for 200 persons recognition, validation accuracy was about 82% without IA and 96.23 with IA. For 800 persons recognition, validation accuracy was 93.62% without IA.

Joint multi-scale discrimination and region segmentation for person re-ID

Abstract Most existing person re-identification methods are mainly based on human part partition with horizontal stripes or human body semantic segmentation. In this paper, we propose a method called MDRS (Multi-scale Discriminative network with Region Segmentation) to integrate multi-scale discriminative feature learning, horizontal stripe partition and semantic segmentation in a single framework, in which multi-scale horizontal stripe partition and usage of both global and local features make the framework be robust to human pose variation, occlusion and background clutter, and semantic segmentation boosts the performance of person identification via shared multi-scale feature extraction. MDRS is trained end-to-end with a multi-task learning strategy that considers three tasks simultaneously: person identification, triplet prediction and pixel-wise semantic segmentation. Comprehensive experiments confirm that our approach exceeds many methods and robustly achieves excellent performances on mainstream evaluation datasets including Market-1501, DukeMTMC-reid and CUHK03.

Effective person re-identification by self-attention model guided feature learning

Person re-identification (re-ID), of which the goal is to recognize person identities of images captured by non-overlapping cameras, is a challenging topic in computer vision. Most existing person re-ID methods conduct directly on detected objects, which ignore the space misalignment caused by detectors, human pose variation, and occlusion problems. To tackle the above mentioned difficulties, we propose a self-attention model guided deep convolutional neural network(DCNN) to learn robust features from image shots. Kernels of the self-attention model evaluate weights for the importance of different person regions. To solve the local feature dependence problem of feature extraction, the non-local feature map generated by the self-attention model is fused with the original feature map generated from the resnet-50. Furthermore, the loss function considers both the cross-entropy loss and the triplet loss in the training process, which enables the network to capture common characteristics within the same individuals and significant differences between distinct persons. Extensive experiments and comparative evaluations show that our proposed strategy outperforms most of the state-of-the-art methods on standard datasets: Market-1501, DukeMTMC-reID, and CUHK03.

Group Reidentification with Multigrained Matching and Integration.

The task of reidentifying groups of people under different camera views is an important yet less-studied problem. Group reidentification (Re-ID) is a very challenging task since it is not only adversely affected by common issues in traditional single-object Re-ID problems, such as viewpoint and human pose variations, but also suffers from changes in group layout and group membership. In this paper, we propose a novel concept of group granularity by characterizing a group image by multigrained objects: individual people and subgroups of two and three people within a group. To achieve robust group Re-ID, we first introduce multigrained representations which can be extracted via the development of two separate schemes, that is, one with handcrafted descriptors and another with deep neural networks. The proposed representation seeks to characterize both appearance and spatial relations of multigrained objects, and is further equipped with importance weights which capture variations in intragroup dynamics. Optimal group-wise matching is facilitated by a multiorder matching process which, in turn, dynamically updates the importance weights in iterative fashion. We evaluated three multicamera group datasets containing complex scenarios and large dynamics, with experimental results demonstrating the effectiveness of our approach.

Attention driven person re-identification

Person re-identification (ReID) is a challenging task due to arbitrary human pose variations, background clutters, etc. It has been studied extensively in recent years, but the multifarious local and global features are still not fully exploited by either ignoring the interplay between whole-body images and body-part images or missing in-depth examination of specific body-part images. In this paper, we propose a novel attention-driven multi-branch network that learns robust and discriminative human representation from global whole-body images and local body-part images simultaneously. Within each branch, an intra-attention network is designed to search for informative and discriminative regions within the whole-body or body-part images, where attention is elegantly decomposed into spatial-wise attention and channel-wise attention for effective and efficient learning. In addition, a novel inter-attention module is designed which fuses the output of intra-attention networks adaptively for optimal person ReID. The proposed technique has been evaluated over three widely used datasets CUHK03, Market-1501 and DukeMTMC-ReID, and experiments demonstrate its superior robustness and effectiveness as compared with the state of the arts.

Deep transformation learning for face recognition in the unconstrained scene

Because human pose variations cannot be controlled in unconstrained scene, it is frequently hard to capture frontal face image. This is why either face recognition rate is low, or face image cannot be recognized at all. To tackle the problem, this paper proposes deep transformation learning to extract the pose-robust feature within one model; it includes feature transformation and joint supervision of softmax loss and pose loss. Specifically, the feature transformation is designed to learn the transformation from different poses. The pose loss is designed to simultaneously learn the feature center of different poses and keep intra-pose relationships. The extracted deep features tend to be more pose-robust and discriminative. Experimental results also confirm the performances to be valid on several important face recognition benchmarks, including Labeled Faces in the Wild, IARPA Janus Benchmark A.

Learning Correspondence Structures for Person Re-Identification

This paper addresses the problem of handling spatial misalignments due to camera-view changes or human-pose variations in person re-identification. We first introduce a boosting-based approach to learn a correspondence structure, which indicates the patchwise matching probabilities between images from a target camera pair. The learned correspondence structure can not only capture the spatial correspondence pattern between cameras but also handle the viewpoint or human-pose variation in individual images. We further introduce a global constraint-based matching process. It integrates a global matching constraint over the learned correspondence structure to exclude cross-view misalignments during the image patch matching process, hence achieving a more reliable matching score between images. Finally, we also extend our approach by introducing a multi-structure scheme, which learns a set of local correspondence structures to capture the spatial correspondence sub-patterns between a camera pair, so as to handle the spatial misalignments between individual images in a more precise way. Experimental results on various data sets demonstrate the effectiveness of our approach.

Multihuman Tracking Based on a Spatial–Temporal Appearance Match

In this paper, we focus on the improvements of appearance representation for multihuman tracking. Many previous methods extracted low-level appearance features, such as color histogram and texture, even combined with spatial information for each frame. These methods ignore the temporal distribution of features. The features of each frame may not be stable due to illumination, human pose variation, and image noise. In order to improve it, we propose a novel appearance representation called the spatial-temporal appearance model based on the statistical distribution of Gaussian mixture model (GMM). It represents the appearance of a tracklet as a whole with dynamic spatial and temporal information. The spatial information is the dynamic subregions. The temporal information is the dynamic duration time of each subregion. Each subregion is modeled as the weighted Gaussian distribution of GMM. The online expectation-maximization (online EM) algorithm is used to estimate the parameters of GMM. Then, we propose a tracklet association method using Bayesian prediction and Jensen-Shannon divergence. The Bayesian prediction is used to predict the locations of targets. The Jensen-Shannon divergence is used to compute the distance of spatial-temporal appearance distribution between two tracklets. Finally, we test our approach on four challenging datasets (TRECVID, CAVIAR, ETH, and EPFL Terrace) and achieve good results.