Bio: Chen Ye is an academic researcher from Tongji University. The author has contributed to research in topics: Smart camera & Video tracking. The author has an hindex of 1, co-authored 2 publications receiving 7 citations.
21 Dec 2013
TL;DR: A real-time video-surveillance system on embedded smart cameras is presented aiming at a wide range of traffic surveillance and monitoring scenarios, in which event detection, vehicle identification and tracking are implemented in front-end cameras.
Abstract: A real-time video-surveillance system on embedded smart cameras is presented aiming at a wide range of traffic surveillance and monitoring scenarios, in which event detection, vehicle identification and tracking are implemented in front-end cameras. In addition, the proposed system transmits the feature information and related video data of events instead of the complete video data, which greatly reduces the usage rate of network bandwidth on video streaming. A demo system with overall architecture and simplified components was implemented. The algorithms, which were used to detect, identify and track vehicles, employed in the demo system include video foreground subtraction, moving vehicle extraction, color features extraction, etc. The real-time constraint of embedded device used in the experiment renders most complex algorithms simplified. In average case, the system achieves about 17 frames per second in embedded smart camera.
••24 Aug 2014
TL;DR: A vehicle tracking mode based on dynamic roles is proposed in the smart camera networks that can effectively decrease the working pressure of server system, reduce the requirements of network bandwidth for real-time video transmission, and make the system flexible and fault-tolerant.
Abstract: A vehicle tracking mode based on dynamic roles is proposed in the smart camera networks. The tracking for a specific vehicle is organized collaboratively and automatically in smart camera network. The tracking is completed autonomously by smart cameras in a distributed manner. The decentralized control mode can effectively decrease the working pressure of server system, reduce the requirements of network bandwidth for real-time video transmission, and make the system flexible and fault-tolerant. An information transmission mechanism is also presented in the smart camera network to ensure the collaborative tracking. Finally, a demo system for vehicle tracking in intelligent traffic surveillance system is implemented to verify the proposed methods.
TL;DR: Several approaches and technologies, namely the Internet of Things, cloud computing, edge computing and big data, are combined into a common framework to enable a unified approach to implementing an ISS at an urban scale, thus paving the way for the metropolitan intelligent surveillance system (MISS).
Abstract: Recent technological advances led to the rapid and uncontrolled proliferation of intelligent surveillance systems (ISSs), serving to supervise urban areas. Driven by pressing public safety and security requirements, modern cities are being transformed into tangled cyber-physical environments, consisting of numerous heterogeneous ISSs under different administrative domains with low or no capabilities for reuse and interaction. This isolated pattern renders itself unsustainable in city-wide scenarios that typically require to aggregate, manage, and process multiple video streams continuously generated by distributed ISS sources. A coordinated approach is therefore required to enable an interoperable ISS for metropolitan areas, facilitating technological sustainability to prevent network bandwidth saturation. To meet these requirements, this paper combines several approaches and technologies, namely the Internet of Things, cloud computing, edge computing and big data, into a common framework to enable a unified approach to implementing an ISS at an urban scale, thus paving the way for the metropolitan intelligent surveillance system (MISS). The proposed solution aims to push data management and processing tasks as close to data sources as possible, thus increasing performance and security levels that are usually critical to surveillance systems. To demonstrate the feasibility and the effectiveness of this approach, the paper presents a case study based on a distributed ISS scenario in a crowded urban area, implemented on clustered edge devices that are able to off-load tasks in a “horizontal” manner in the context of the developed MISS framework. As demonstrated by the initial experiments, the MISS prototype is able to obtain face recognition results 8 times faster compared with the traditional off-loading pattern, where processing tasks are pushed “vertically” to the cloud.
TL;DR: A novel framework for vehicle counting based on aerial videos is proposed, which can achieve more than 90% and 85% accuracy of vehicle counting in fixed-background videos and moving- Background videos respectively.
Abstract: Vehicle counting from an unmanned aerial vehicle (UAV) is becoming a popular research topic in traffic monitoring. Camera mounted on UAV can be regarded as a visual sensor for collecting aerial videos. Compared with traditional sensors, the UAV can be flexibly deployed to the areas that need to be monitored and can provide a larger perspective. In this paper, a novel framework for vehicle counting based on aerial videos is proposed. In our framework, the moving-object detector can handle the following two situations: static background and moving background. For static background, a pixel-level video foreground detector is given to detect vehicles, which can update background model continuously. For moving background, image-registration is employed to estimate the camera motion, which allows the vehicles to be detected in a reference coordinate system. In addition, to overcome the change of scale and shape of vehicle in images, we employ an online-learning tracker which can update the samples used for training. Finally, we design a multi-object management module which can efficiently analyze and validate the status of the tracked vehicles with multi-threading technique. Our method was tested on aerial videos of real highway scenes that contain fixed-background and moving-background. The experimental results show that the proposed method can achieve more than 90% and 85% accuracy of vehicle counting in fixed-background videos and moving-background videos respectively.
TL;DR: This paper addresses some of the challenges faced in the IoT infrastructure, specifically secure communication and user authentication in the context of automated analysis of biomedical images and communication of the analysis results and related metadata in a smart healthcare framework.
Abstract: Smart Healthcare is envisioned as the combination of traditional healthcare augmented by smart bio-sensors, wearable devices, and a plethora of on-body sensors that communicate with smart hospitals, smart emergency response systems, and ambulances, through advanced information and communication technologies. The vision of smart healthcare as part of a smart city relies on the framework of the Internet of Things (IoT) as the underlying core technology that enables the design and operation of a city, whereby smart technology, energy grids, transportation, buildings, communication, and information technology, are all interconnected. This paper addresses some of the challenges faced in the IoT infrastructure, specifically secure communication and user authentication in the context of automated analysis of biomedical images and communication of the analysis results and related metadata in a smart healthcare framework. A hardware architecture for a secure digital camera integrated with the secure better portable graphics (SBPG) compression algorithm, suitable for applications in the IoT, is proposed in this paper. The focus of this paper is on patient data protection and authentication. The proposed SBPG architecture offers two layers of protection, concurrent encryption and watermarking, which address all issues related to security, privacy, and digital rights management. The experimental results demonstrate that the new compression technique BPG outperforms JPEG in terms of compression quality and compressed file size while providing increased image quality. High performance requirements of BPG have been met by employing two techniques: 1) insertion of an encrypted signature in the center portion of the image and 2) frequency-domain watermarking using blockwise DCT of size $8\times 8$ pixels. These approaches optimize the proposed architecture by decreasing computational complexity while maintaining strong protection, with concomitant increase of the speed of the watermarking and compression processes. A Simulink® prototype for the proposed architecture has been built and tested. To the best of our knowledge, the hardware architecture for BPG compression with built-in image authentication capability for integration with a secure digital camera is the first one ever proposed .
18 Apr 2016
TL;DR: The experimental results prove that the new compression technique BPG outperforms JPEG in terms of compression quality and size of the compression file.
Abstract: This paper proposes a hardware architecture for a Secure Digital Camera (SDC) integrated with Secure Better Portable Graphics (SBPG) compression algorithm. The proposed architecture is suitable for high performance imaging in the Internet of Things (IoT). The objectives of this paper are twofold. On the one hand, the proposed SBPG architecture offers double-layer protection: encryption and watermarking. On the other hand, the paper proposes SDC integrated with secure BPG compression for real time intelligent traffic surveillance (ITS). The experimental results prove that the new compression technique BPG outperforms JPEG in terms of compression quality and size of the compression file. As the visual quality of the watermarked and compressed images improves with larger values of PSNR, the results show that the proposed SBPG substantially increases the quality of the watermarked compressed images. To achieve a high performance architecture three techniques are considered: first, using the center portion of the image to insert the encrypted signature. Second, watermarking is done in the frequency domain using block-wise DCT size 8×8. Third, in BPG encoder, the proposed architecture uses inter and intra prediction to reduce the temporal and spatial redundancy.
•01 Jan 2013
TL;DR: In this article, the authors describe how an existing agent platform has been adopted and used to carry out intelligent surveillance in urban traffic environments, where agents implement a behavior-based model that is flexible enough to deal with the challenges that the surveillance tasks pose.
Abstract: Intelligent surveillance aims at providing artificial systems in order to monitor and improve the security of public and private spaces. Since these environments are complex and the information is distributed through them, agent-based solutions represent a good approach when monitoring moving objects. This paper describes how an existing agent platform has been adopted and used to carry out intelligent surveillance. Within this context, agents implement a behavior-based model that is flexible enough to deal with the challenges that the surveillance tasks pose. The experimental results show how this agent-based approach can contribute to understand events in urban traffic environments.