Robust and Efficient Graph Correspondence Transfer for Person Re-Identification.

Spatial misalignment caused by variations in poses and viewpoints is one of the most critical issues that hinder the performance improvement in existing person re-identification (Re-ID) algorithms. Although it is straightforward to explore correspondence learning algorithms for alignment, online learning is intractable for negative pairs due to the intrinsic visual difference between negative pairs and efficiency concern. To address this problem, in this paper, we present a robust and efficient graph correspondence transfer (REGCT) approach for explicit spatial alignment in Re-ID. Specifically, we propose the off-line correspondence learning and on-line correspondence transfer framework. During training, patch-wise correspondences between positive training pairs are established via graph matching. By exploiting both spatial and visual contexts of human appearance in graph matching, meaningful semantic correspondences can be obtained. During testing, the off-line learned patch-wise correspondence templates are transferred to test pairs with similar pose-pair configurations for local feature distance calculation. To enhance the robustness of correspondence transfer, we design a novel pose context descriptor to accurately model human body configurations, and present an approach to measure the similarity between a pair of pose context descriptors. Meanwhile, to improve testing efficiency, we propose a correspondence template ensemble method using the voting mechanism, which significantly reduces the amount of patch-wise matchings involved in distance calculation. With the aforementioned strategies, the REGCT model can effectively and efficiently handle the spatial misalignment problem in Re-ID. Extensive experiments on five challenging benchmarks, including VIPeR, Road, PRID450S, 3DPES, and CUHK01, evidence the superior performance of REGCT over other state-of-the-art approaches.

Incremental structured dictionary learning for video sensor-based object tracking.

To tackle robust object tracking for video sensor-based applications, an online discriminative algorithm based on incremental discriminative structured dictionary learning (IDSDL-VT) is presented. In our framework, a discriminative dictionary combining both positive, negative and trivial patches is designed to sparsely represent the overlapped target patches. Then, a local update (LU) strategy is proposed for sparse coefficient learning. To formulate the training and classification process, a multiple linear classifier group based on a K-combined voting (KCV) function is proposed. As the dictionary evolves, the models are also trained to timely adapt the target appearance variation. Qualitative and quantitative evaluations on challenging image sequences compared with state-of-the-art algorithms demonstrate that the proposed tracking algorithm achieves a more favorable performance. We also illustrate its relay application in visual sensor networks.

Interactive cell segmentation based on phase contrast optics.

Cell segmentation in phase contrast microscopy images lays a crucial foundation for numerous subsequent computer-aided cell image analysis, but it encounters many unsolved challenges due to image qualities and artifacts caused by phase contrast optics. Addressing the unsolved challenges, the authors propose an interactive cell segmentation scheme over phase retardation features. After partitioning the images into phase homogeneous atoms, human annotations are propagated to unlabeled atoms over an affinity graph that is learned based on discrimination analysis. Then, an active query strategy is proposed for which the most informative unlabeled atom is selected for annotation, which is also propagated to the other unlabeled atoms. Cell segmentation converges to quality results after several rounds of interactions involving both the user's intentions and characteristics of image features. Experimental results demonstrate that cells with different optical properties are well segmented via the proposed approach.

Video sensor-based complex scene analysis with Granger causality.

In this report, we propose a novel framework to explore the activity interactions and temporal dependencies between activities in complex video surveillance scenes. Under our framework, a low-level codebook is generated by an adaptive quantization with respect to the activeness criterion. The Hierarchical Dirichlet Processes (HDP) model is then applied to automatically cluster low-level features into atomic activities. Afterwards, the dynamic behaviors of the activities are represented as a multivariate point-process. The pair-wise relationships between activities are explicitly captured by the non-parametric Granger causality analysis, from which the activity interactions and temporal dependencies are discovered. Then, each video clip is labeled by one of the activity interactions. The results of the real-world traffic datasets show that the proposed method can achieve a high quality classification performance. Compared with traditional K-means clustering, a maximum improvement of 19.19% is achieved by using the proposed causal grouping method.