Rui Zhao

Unsupervised Salience Learning for Person Re-identification

Human eyes can recognize person identities based on some small salient regions. However, such valuable salient information is often hidden when computing similarities of images with existing approaches. Moreover, many existing approaches learn discriminative features and handle drastic viewpoint change in a supervised way and require labeling new training data for a different pair of camera views. In this paper, we propose a novel perspective for person re-identification based on unsupervised salience learning. Distinctive features are extracted without requiring identity labels in the training procedure. First, we apply adjacency constrained patch matching to build dense correspondence between image pairs, which shows effectiveness in handling misalignment caused by large viewpoint and pose variations. Second, we learn human salience in an unsupervised manner. To improve the performance of person re-identification, human salience is incorporated in patch matching to find reliable and discriminative matched patches. The effectiveness of our approach is validated on the widely used VIPeR dataset and ETHZ dataset.

DeepReID: Deep Filter Pairing Neural Network for Person Re-identification

Person re-identification is to match pedestrian images from disjoint camera views detected by pedestrian detectors. Challenges are presented in the form of complex variations of lightings, poses, viewpoints, blurring effects, image resolutions, camera settings, occlusions and background clutter across camera views. In addition, misalignment introduced by the pedestrian detector will affect most existing person re-identification methods that use manually cropped pedestrian images and assume perfect detection. In this paper, we propose a novel filter pairing neural network (FPNN) to jointly handle misalignment, photometric and geometric transforms, occlusions and background clutter. All the key components are jointly optimized to maximize the strength of each component when cooperating with others. In contrast to existing works that use handcrafted features, our method automatically learns features optimal for the re-identification task from data. The learned filter pairs encode photometric transforms. Its deep architecture makes it possible to model a mixture of complex photometric and geometric transforms. We build the largest benchmark re-id dataset with 13, 164 images of 1, 360 pedestrians. Unlike existing datasets, which only provide manually cropped pedestrian images, our dataset provides automatically detected bounding boxes for evaluation close to practical applications. Our neural network significantly outperforms state-of-the-art methods on this dataset.

Person Re-identification by Salience Matching

Human salience is distinctive and reliable information in matching pedestrians across disjoint camera views. In this paper, we exploit the pair wise salience distribution relationship between pedestrian images, and solve the person re-identification problem by proposing a salience matching strategy. To handle the misalignment problem in pedestrian images, patch matching is adopted and patch salience is estimated. Matching patches with inconsistent salience brings penalty. Images of the same person are recognized by minimizing the salience matching cost. Furthermore, our salience matching is tightly integrated with patch matching in a unified structural Rank SVM learning framework. The effectiveness of our approach is validated on the VIPeR dataset and the CUHK Campus dataset. It outperforms the state-of-the-art methods on both datasets.

Learning Mid-level Filters for Person Re-identification

In this paper, we propose a novel approach of learning mid-level filters from automatically discovered patch clusters for person re-identification. It is well motivated by our study on what are good filters for person re-identification. Our mid-level filters are discriminatively learned for identifying specific visual patterns and distinguishing persons, and have good cross-view invariance. First, local patches are qualitatively measured and classified with their discriminative power. Discriminative and representative patches are collected for filter learning. Second, patch clusters with coherent appearance are obtained by pruning hierarchical clustering trees, and a simple but effective cross-view training strategy is proposed to learn filters that are view-invariant and discriminative. Third, filter responses are integrated with patch matching scores in RankSVM training. The effectiveness of our approach is validated on the VIPeR dataset and the CUHK01 dataset. The learned mid-level features are complementary to existing handcrafted low-level features, and improve the best Rank-1 matching rate on the VIPeR dataset by 14%.

Human reidentification with transferred metric learning

Human reidentification is to match persons observed in non-overlapping camera views with visual features for inter-camera tracking. The ambiguity increases with the number of candidates to be distinguished. Simple temporal reasoning can simplify the problem by pruning the candidate set to be matched. Existing approaches adopt a fixed metric for matching all the subjects. Our approach is motivated by the insight that different visual metrics should be optimally learned for different candidate sets. We tackle this problem under a transfer learning framework. Given a large training set, the training samples are selected and reweighted according to their visual similarities with the query sample and its candidate set. A weighted maximum margin metric is online learned and transferred from a generic metric to a candidate-set-specific metric. The whole online reweighting and learning process takes less than two seconds per candidate set. Experiments on the VIPeR dataset and our dataset show that the proposed transferred metric learning significantly outperforms directly matching visual features or using a single generic metric learned from the whole training set.

Saliency detection by multi-context deep learning

Low-level saliency cues or priors do not produce good enough saliency detection results especially when the salient object presents in a low-contrast background with confusing visual appearance. This issue raises a serious problem for conventional approaches. In this paper, we tackle this problem by proposing a multi-context deep learning framework for salient object detection. We employ deep Convolutional Neural Networks to model saliency of objects in images. Global context and local context are both taken into account, and are jointly modeled in a unified multi-context deep learning framework. To provide a better initialization for training the deep neural networks, we investigate different pre-training strategies, and a task-specific pre-training scheme is designed to make the multi-context modeling suited for saliency detection. Furthermore, recently proposed contemporary deep models in the ImageNet Image Classification Challenge are tested, and their effectiveness in saliency detection are investigated. Our approach is extensively evaluated on five public datasets, and experimental results show significant and consistent improvements over the state-of-the-art methods.

Person Re-Identification by Saliency Learning

Human eyes can recognize person identities based on small salient regions, i.e., person saliency is distinctive and reliable in pedestrian matching across disjoint camera views. However, such valuable information is often hidden when computing similarities of pedestrian images with existing approaches. Inspired by our user study result of human perception on person saliency, we propose a novel perspective for person re-identification based on learning person saliency and matching saliency distribution. The proposed saliency learning and matching framework consists of four steps: (1) To handle misalignment caused by drastic viewpoint change and pose variations, we apply adjacency constrained patch matching to build dense correspondence between image pairs. (2) We propose two alternative methods, i.e., K-Nearest Neighbors and One-class SVM, to estimate a saliency score for each image patch, through which distinctive features stand out without using identity labels in the training procedure. (3) saliency matching is proposed based on patch matching. Matching patches with inconsistent saliency brings penalty, and images of the same identity are recognized by minimizing the saliency matching cost. (4) Furthermore, saliency matching is tightly integrated with patch matching in a unified structural RankSVM learning framework. The effectiveness of our approach is validated on the four public datasets. Our approach outperforms the state-of-the-art person re-identification methods on all these datasets.Human eyes can recognize person identities based on small salient regions, i.e., person saliency is distinctive and reliable in pedestrian matching across disjoint camera views. However, such valuable information is often hidden when computing similarities of pedestrian images with existing approaches. Inspired by our user study result of human perception on person saliency, we propose a novel perspective for person re-identification based on learning person saliency and matching saliency distribution. The proposed saliency learning and matching framework consists of four steps: (1) To handle misalignment caused by drastic viewpoint change and pose variations, we apply adjacency constrained patch matching to build dense correspondence between image pairs. (2) We propose two alternative methods, i.e., K-Nearest Neighbors and One-class SVM, to estimate a saliency score for each image patch, through which distinctive features stand out without using identity labels in the training procedure. (3) saliency matching is proposed based on patch matching. Matching patches with inconsistent saliency brings penalty, and images of the same identity are recognized by minimizing the saliency matching cost. (4) Furthermore, saliency matching is tightly integrated with patch matching in a unified structural RankSVM learning framework. The effectiveness of our approach is validated on the four public datasets. Our approach outperforms the state-of-the-art person re-identification methods on all these datasets.

Person Re-identification: System Design and Evaluation Overview

Person re-identification has important applications in video surveillance. It is particularly challenging because observed pedestrians undergo significant variations across camera views, and there are a large number of pedestrians to be distinguished given small pedestrian images from surveillance videos. This chapter discusses different approaches of improving the key components of a person re-identification system, including feature design, feature learning, and metric learning, as well as their strength and weakness. It provides an overview of various person re-identification systems and their evaluation on benchmark datasets. Multiple benchmark datasets for person re-identification are summarized and discussed. The performance of some state-of-the-art person identification approaches on benchmark datasets is compared and analyzed. It also discusses a few future research directions on improving benchmark datasets, evaluation methodology, and system design.

Counting Vehicles from Semantic Regions

Automatically counting vehicles in complex traffic scenes from videos is challenging. Detection and tracking algorithms may fail due to occlusions, scene clutters, and large variations of viewpoints and vehicle types. We propose a new approach of counting vehicles through exploiting contextual regularities from scene structures. It breaks the problem into simpler problems, which count vehicles on each path separately. The model of each path and its source and sink add strong regularization on the motion and the sizes of vehicles and can thus significantly improve the accuracy of vehicle counting. Our approach is based on tracking and clustering feature points and can be summarized in threefold. First, an algorithm is proposed to automatically learn the models of scene structures. A traffic scene is segmented into local semantic regions by exploiting the temporal cooccurrence of local motions. Local semantic regions are connected into global complete paths using the proposed fast marching algorithm. Sources and sinks are estimated from the models of semantic regions. Second, an algorithm is proposed to cluster trajectories of feature points into objects and to estimate average vehicle sizes at different locations from initial clustering results. Third, trajectories of features points are often fragmented due to occlusions. By integrating the spatiotemporal features of trajectory clusters with contextual models of paths and sources and sinks, trajectory clusters are assigned into different paths and connected into complete trajectories. Experimental results on a complex traffic scene show the effectiveness of our approach.

Crossing-Line Crowd Counting with Two-Phase Deep Neural Networks

In this paper, we propose a deep Convolutional Neural Network (CNN) for counting the number of people across a line-of-interest (LOI) in surveillance videos. It is a challenging problem and has many potential applications. Observing the limitations of temporal slices used by state-of-the-art LOI crowd counting methods, our proposed CNN directly estimates the crowd counts with pairs of video frames as inputs and is trained with pixel-level supervision maps. Such rich supervision information helps our CNN learn more discriminative feature representations. A two-phase training scheme is adopted, which decomposes the original counting problem into two easier sub-problems, estimating crowd density map and estimating crowd velocity map. Learning to solve the sub-problems provides a good initial point for our CNN model, which is then fine-tuned to solve the original counting problem. A new dataset with pedestrian trajectory annotations is introduced for evaluating LOI crowd counting methods and has more annotations than any existing one. Our extensive experiments show that our proposed method is robust to variations of crowd density, crowd velocity, and directions of the LOI, and outperforms state-of-the-art LOI counting methods.