arXiv subjects

Zhang Zhang

Publications and source records attributed to Zhang Zhang.

113 records · Page 7Linked to original sources

arXiv2016

A Large-scale Distributed Video Parsing and Evaluation Platform

Visual surveillance systems have become one of the largest data sources of Big Visual Data in real world. However, existing systems for video analysis still lack the ability to handle the problems of scalability, expansibility and error-prone, though great advances have been achieved in a number of visual recognition tasks and surveillance applications, e.g., pedestrian/vehicle detection, people/vehicle counting. Moreover, few algorithms explore the specific values/characteristics in large-scale surveillance videos. To address these problems in large-scale video analysis, we develop a scalable video parsing and evaluation platform through combining some advanced techniques for Big Data processing, including Spark Streaming, Kafka and Hadoop Distributed Filesystem (HDFS). Also, a Web User Interface is designed in the system, to collect users' degrees of satisfaction on the recognition tasks so as to evaluate the performance of the whole system. Furthermore, the highly extensible platform running on the long-term surveillance videos makes it possible to develop more intelligent incremental algorithms to enhance the performance of various visual recognition tasks.

cs.CV↗

arXiv2016

Weakly-supervised Learning of Mid-level Features for Pedestrian Attribute Recognition and Localization

State-of-the-art methods treat pedestrian attribute recognition as a multi-label image classification problem. The location information of person attributes is usually eliminated or simply encoded in the rigid splitting of whole body in previous work. In this paper, we formulate the task in a weakly-supervised attribute localization framework. Based on GoogLeNet, firstly, a set of mid-level attribute features are discovered by novelly designed detection layers, where a max-pooling based weakly-supervised object detection technique is used to train these layers with only image-level labels without the need of bounding box annotations of pedestrian attributes. Secondly, attribute labels are predicted by regression of the detection response magnitudes. Finally, the locations and rough shapes of pedestrian attributes can be inferred by performing clustering on a fusion of activation maps of the detection layers, where the fusion weights are estimated as the correlation strengths between each attribute and its relevant mid-level features. Extensive experiments are performed on the two currently largest pedestrian attribute datasets, i.e. the PETA dataset and the RAP dataset. Results show that the proposed method has achieved competitive performance on attribute recognition, compared to other state-of-the-art methods. Moreover, the results of attribute localization are visualized to understand the characteristics of the proposed method.

cs.CV↗

arXiv2016

A Richly Annotated Dataset for Pedestrian Attribute Recognition

In this paper, we aim to improve the dataset foundation for pedestrian attribute recognition in real surveillance scenarios. Recognition of human attributes, such as gender, and clothes types, has great prospects in real applications. However, the development of suitable benchmark datasets for attribute recognition remains lagged behind. Existing human attribute datasets are collected from various sources or an integration of pedestrian re-identification datasets. Such heterogeneous collection poses a big challenge on developing high quality fine-grained attribute recognition algorithms. Furthermore, human attribute recognition are generally severely affected by environmental or contextual factors, such as viewpoints, occlusions and body parts, while existing attribute datasets barely care about them. To tackle these problems, we build a Richly Annotated Pedestrian (RAP) dataset from real multi-camera surveillance scenarios with long term collection, where data samples are annotated with not only fine-grained human attributes but also environmental and contextual factors. RAP has in total 41,585 pedestrian samples, each of which is annotated with 72 attributes as well as viewpoints, occlusions, body parts information. To our knowledge, the RAP dataset is the largest pedestrian attribute dataset, which is expected to greatly promote the study of large-scale attribute recognition systems. Furthermore, we empirically analyze the effects of different environmental and contextual factors on pedestrian attribute recognition. Experimental results demonstrate that viewpoints, occlusions and body parts information could assist attribute recognition a lot in real applications.

cs.CV↗

arXiv2014

An ESPRIT-Based Approach for 2-D Localization of Incoherently Distributed Sources in Massive MIMO Systems

In this paper, an approach of estimating signal parameters via rotational invariance technique (ESPRIT) is proposed for two-dimensional (2-D) localization of incoherently distributed (ID) sources in large-scale/massive multiple-input multiple-output (MIMO) systems. The traditional ESPRIT-based methods are valid only for one-dimensional (1-D) localization of the ID sources. By contrast, in the proposed approach the signal subspace is constructed for estimating the nominal azimuth and elevation direction-of-arrivals and the angular spreads. The proposed estimator enjoys closed-form expressions and hence it bypasses the searching over the entire feasible field. Therefore, it imposes significantly lower computational complexity than the conventional 2-D estimation approaches. Our analysis shows that the estimation performance of the proposed approach improves when the large-scale/massive MIMO systems are employed. The approximate Cramér-Rao bound of the proposed estimator for the 2-D localization is also derived. Numerical results demonstrate that albeit the proposed estimation method is comparable with the traditional 2-D estimators in terms of performance, it benefits from a remarkably lower computational complexity.

cs.IT↗

arXiv2013

A low complexity approach of combining cooperative diversity and multiuser diversity in multiuser cooperative networks

In this paper, we investigate the scheduling scheme to combine cooperative diversity (CD) and multiuser diversity (MUD) in multiuser cooperative networks under the time resource allocation (TRA) framework in which the whole transmission is divided into two phases: the broadcast phase and the relay phase. The broadcast phase is for direct transmission whereas the relay phase is for relay transmission. Based on this TRA framework, a user selection based low complexity relay protocol (US-LCRP) is proposed to combine CD and MUD. In each time slot (TS) of the broadcast phase, a "best" user is selected for transmission in order to obtain MUD. In the relay phase, the relays forward the messages of some specific users in a fixed order and then invoke the limited feedback information to achieve CD. We demonstrate that the diversity-multiplexing tradeoff (DMT) of the US-LCRP is superior to that of the existing schemes, where more TSs are allocated for direct transmission in order to jointly exploit CD and MUD. Our analytical and numerical results show that the US-LCRP constitutes a more efficient resource utilization approach than the existing schemes. Additionally, the US-LCRP can be implemented with low complexity because only the direct links' channel state information (CSI) is estimated during the whole transmission.

cs.IT↗