Qingming Yao

Video processing techniques for traffic flow monitoring: A survey

Video-based traffic flow monitoring is a fast emerging field based on the continuous development of computer vision. A survey of the state-of-the-art video processing techniques in traffic flow monitoring is presented in this paper. Firstly, vehicle detection is the first step of video processing and detection methods are classified into background modeling based methods and non-background modeling based methods. In particular, nighttime detection is more challenging due to bad illumination and sensitivity to light. Then tracking techniques, including 3D model-based, region-based, active contour-based and feature-based tracking, are presented. A variety of algorithms including MeanShift algorithm, Kalman Filter and Particle Filter are applied in tracking process. In addition, shadow detection and vehicles occlusion bring much trouble into vehicle detection, tracking and so on. Based on the aforementioned video processing techniques, discussion on behavior understanding including traffic incident detection is carried out. Finally, key challenges in traffic flow monitoring are discussed.

Vehicle Detection Based on the and– or Graph for Congested Traffic Conditions

In urban traffic video monitoring systems, traffic congestion is a common scene that causes vehicle occlusion and is a challenge for current vehicle detection methods. To solve the occlusion problem in congested traffic conditions, we have proposed an effective vehicle detection approach based on an and -or graph (AOG) in this paper. Our method includes three steps: constructing an AOG for representing vehicle objects in the congested traffic condition; training parameters in the AOG; and, finally, detecting vehicles using bottom-up inference. In AOG construction, sophisticated vehicle feature selection avoids using the easily occluded vehicle components but takes highly visible components into account. The vehicles are well represented by these selected vehicle features in the presence of a congested condition with serious vehicle occlusion. Furthermore, a hierarchical decomposition of the vehicle representation is proposed during AOG construction to further reduce the impact of vehicle occlusion. After AOG construction, all parameters in the AOG are manually learned from the training images or set and further applied to the bottom-up vehicle inference. There are two innovations of our method, i.e., the usage of the AOG in vehicle detection under congested traffic conditions and the special vehicle feature selection for vehicle representation. To fully test our method, we have done a quantitative experiment under a variety of traffic conditions, a contrast experiment, and several experiments on congested conditions. The experimental results illustrate that our method can effectively deal with various vehicle poses, vehicle shapes, and time-of-day and weather conditions. In particular, our approach performs well in congested traffic conditions with serious vehicle occlusion.

Location estimation in ZigBee Network based on fingerprinting

Location-aware computing becomes an exciting research as recent advancements in RF circuits and wireless communication stacks. In this paper, we present a fingerprinting based location estimation technology in ZigBee network. The system uses the signal strength from several base stations rather than time or angle for determining the location of mobile station. Instead of modeling the complex attenuation of signal strength, the system models the probabilistic distribution in different geographical areas which we called fingerprinting. It combines the measured data and fingerprinting to determine the mobile stations location. The experiment results demonstrate the validity of location estimation in ZigBee network based on fingerprinting.

A vehicle license plate recognition system based on analysis of maximally stable extremal regions

Vehicle License Plate Recognition (VLPR) system is a core module in Intelligent Transportation Systems (ITS). In this paper, a VLPR system is proposed. Considering that license plate localization is the most important and difficult part in VLPR system, we present an effective license plate localization method based on analysis of Maximally Stable Extremal Region (MSER) features. Firstly, MSER detector is utilized to extract candidate character regions. Secondly, the exact locations of license plates are inferred according to the arrangement of characters in standard license plates. The advantage of this license plate localization method is that less assumption of environmental illumination, weather and other conditions is made. After license plate localization, we continue to recognize the license plate characters and color to complete the whole VLPR system. Finally, the proposed VLPR system is tested on our own collected dataset. The experimental results show the availability and effectiveness of our VLPR system in locating and recognizing all the explicit license plates in an image.

A review on vision-based pedestrian detection in intelligent transportation systems

Pedestrians are key participants in transportation systems, so pedestrian detection in video surveillance systems is of great significance to the research and application of Intelligent Transportation Systems (ITS). We review some methods and models for vision-based pedestrian detection in recent years. In this paper, the pedestrian detection techniques are divided into macroscopic and microscopic according to different application in transportation systems. Macroscopic pedestrian detection aims to estimate crowd density without distinguishing each pedestrian, and microscopic pedestrian detection focuses on detection and recognition of individual pedestrians. The latter detection style is deeply studied, so it is presented in detail in this paper, especially for the feature-classifier-based detection method. Finally, the pedestrian detection algorithms are discussed and concluded from the viewpoint of video surveillance and ITS. Existing problems and future trends are presented in that section.

An automated vehicle counting system for traffic surveillance

The objective of this paper is to present a detailed description of using DSP board and image processing techniques to construct an automated vehicle counting system. Such a system has many potential applications, such as traffic signal control and district traffic abduction. We use TITMS320DM642 DSP as the computational unit to avoid heavy investment in industrial control computer while obtaining improved computational power and optimized system structure. The overall software is comprised of two parts: embedded DSP software and host PC software. The embedded DSP software acquires the video image from stationary cameras, detects and counts moving vehicles, and transmits the processing results and realtime images after compression to PC software through network. The host PC software works as a graphic user interface through which the end user can configure the DSP board parameters and access the video processing results. The vehicle detection and counting algorithm is carefully devised to keep robust and efficient in traffic scenes for longtime span and with changeful illumination. Experimental results show that the proposed system performs well in actual traffic scenes, and the processing speed and accuracy of the system can meet the requirement of practical applications.

Fast double-parallel image processing based on FPGA

Due to FPGAs flexibility and parallelism, it is popular for accelerating image processing. In this paper, a double-parallel architecture based on FPGA has been exploited to speed up median filter and edge detection tasks, which are essential steps during image processing. The double-parallel scheme includes an image-level parallel and an operation-level parallel. The image-level parallel is a high-level parallel which divides one image into different parts and processes them concurrently. The operation-level parallel, which is embedded in each image-level parallel thread, fully explores every parallel part inside the concrete algorithms. The corresponding design is based on a DE2 Development Board which contains a CYCLONE II FPGA device. Meanwhile, the same task has also been implemented on PC and DSP for performance comparison. Despite the fact that operating frequencies of used PC and DSP are much higher than FPGAs, FPGA costs less time per computed image than both of them. By taking advantage of the double-parallel technique, the speed/frequency ratio of FPGA is 202 times faster than PC and 147 times faster than DSP. Finally, a detailed discussion about different platforms is conducted, which analyzes advantages and disadvantages of used computing platforms. This paper reveals that the proposed double-parallel scheme can dramatically speed up image processing methods even on a low-cost FPGA platform with low frequency and limited resources, which is very meaningful for practical applications.

MODEL: moving object detection and localization in wireless networks based on small-scale fading

This paper presents a new Moving Object Detection and Localization (MODEL) system, which is based on the smallscale fading of RF signal strength and independent from the salient characteristics of both the device and the sensor. We first validated the feasibility of applying small-scale fading effects to moving object detection and localization through experimental analysis. Then, we introduced MODEL: an embedded network system which adopts an easily-realized Rolling-Window algorithm. We applied the Region-Partition method to determine the position of the moving object, and concluded that the precision of the object position is dependant upon the density of participating nodes. MODEL is also scalable to other wireless network infrastructures and adaptable to various environments without the need for complex and time consuming training.

Rear lamp based vehicle detection and tracking for complex traffic conditions

In video surveillance system, detection and tracking of vehicles are two foundational and significant tasks. In this paper, a vehicle detection and tracking method based on rear lamp pairs is proposed. The proposed method combines color with motion information to perform vehicle detection. In order to adapt to different weather conditions like night, the rear lamps are divided into two categories: unlit lamps and lighted lamps. First, threshold segmentation are used to extract both the unlit and lighted lamp candidates in hue-saturation-value (HSV) color space and the thresholds are selected automatically by maximally stable extremal region (MSER) method. Then, all lamp candidates are tracked by using Kalman filter and lamp candidates with short-lived trajectories are removed to avoid disturbances. Next, two adjacent lamp candidates with similar speed are bound together as a region of interest (ROI), which represents a potential pair of lamps. Image cross-correlation symmetry analysis based on Gabor filter is utilized to find the ROIs with symmetrical texture and these symmetric ROIs can be regarded as pairs of lamps. The experimental results show that the proposed method can effectively deal with various illumination conditions and improve the accuracy and robustness of vehicle detection. In addition, this method can perform vehicle detection and tracking under complex traffic conditions and the Gabor filter based symmetry analysis can successfully suppress subtle difference between the left and right parts of a vehicle as well as environment noises.

Data aggregation technologies of wireless multimedia sensor networks: A survey

The advance in CMOS camera and wireless sensor network (WSN) has promoted the development of wireless multimedia sensor network (WMSN), which can collect more abundant video data and image data. One important enabling technology for WMSN is data aggregation, which is essential for WMSN to be reusable and cost-efficient. The data aggregation technologies can be divided into three parts, namely, data acquisition, data transmission and data processing. This paper presents the state of the art in data aggregation of WMSN according to this category.