A DSP-based system for the detection of vehicles parked in prohibited areas

Sanchis

IEEE Trans. Intell. Transport. Syst.

et al. 2011

This paper presents a video-based approach to detect the presence of parked vehicles in street lanes.Potential applications include detection of illegally and double-parked vehicles in urban scenarios and incident detection on roads. The technique extracts information from low-level feature points (Harris corners) in order to create spatio-temporal maps that describe what is happening in the scene.The method does not rely on any background subtraction or perform any form of object tracking.The system has been evaluated using private and public data sets and has proven to be robust against common difficulties found in CCTV video such as varying illumination, camera vibration, presence of momentary occlusion by other vehicles, and high noise levels.

“…In order to compare our results with those obtained by other researchers such as [8], [9], [10], [11], [12] and [16], our method has also been tested using the sample i-LIDS subset. …”

Section: B Results On I-lids Sample Data Setmentioning

confidence: 88%

Section: Previous Workmentioning

confidence: 99%

See 1 more Smart Citation

Detection of Parked Vehicles Using Spatiotemporal Maps

Sanchis

IEEE Trans. Intell. Transport. Syst.

et al. 2011

“…In Borango et al [8] described the system for automatic robust video Surveillance and its application to the problem of locating vehicles that stop in prohibited area. In this paper, Ipsotek Visual Intelligence Platform is used for video processing, alarm generation and interfacing with the operator.…”

Section: Previous Workmentioning

confidence: 99%

Comparative Analysis and Detection of Street Parked Vehicles using Spatiotemporal Maps and Corner Detection Methods

Jayebhaye¹,

Banwaskar²

2016

IJCA

Traffic control and efficient use of existing infrastructure are key challenges in recent time. This work carries out comparative analysis of various corner detection methods in different conditions, to detect presence of parked vehicles in street lanes. Different algorithmic implementations are used, to detect corners over targets in video stream and then classify them over a spatio-temporal analysis maps to identify parked vehicles. The system has been evaluated using i-Lids public dataset and has proven to be robust against common difficulties found in Closed Circuit Television (CCTV) such as high noise levels, varying illumination and the presence of momentary occlusion by other vehicles. This could be used to detect illegal and double-parked vehicles in metropolitan areas and to detect incidents on roads with lanes. This paper implemented three corner detection algorithms, Harris, SIFT and FAST and analyzed the comparative performances of all three implementations over different parameters viz. precision, recall, false alarm and then conclude on best performing algorithm. The comparative results are presented.

“…The GPU-based parallel computation was implemented using the CUDA toolkit V5.5 (Nvidia, Santa Clara, CA, USA). Figure 10 shows the experimental results of the proposed methods, which were executed on several typical and challenging scenarios from a crowd dataset (PETS2009) [40], vehicle dataset (AVSS2007, London, UK) [41], jug dataset (ICCV2003, Nice, France) [42], and WaveTree dataset (Microsoft Research, Redmond, WA, USA) [43], from left to right. In these datasets, the camera viewports were stationary.…”

Section: Foreground Segmentation Performance Analysismentioning

confidence: 99%

GPU-Accelerated Foreground Segmentation and Labeling for Real-Time Video Surveillance

Song

Tian

Fong³

et al. 2016

Sustainability

Real-time and accurate background modeling is an important researching topic in the fields of remote monitoring and video surveillance. Meanwhile, effective foreground detection is a preliminary requirement and decision-making basis for sustainable energy management, especially in smart meters. The environment monitoring results provide a decision-making basis for energy-saving strategies. For real-time moving object detection in video, this paper applies a parallel computing technology to develop a feedback foreground-background segmentation method and a parallel connected component labeling (PCCL) algorithm. In the background modeling method, pixel-wise color histograms in graphics processing unit (GPU) memory is generated from sequential images. If a pixel color in the current image does not locate around the peaks of its histogram, it is segmented as a foreground pixel. From the foreground segmentation results, a PCCL algorithm is proposed to cluster the foreground pixels into several groups in order to distinguish separate blobs. Because the noisy spot and sparkle in the foreground segmentation results always contain a small quantity of pixels, the small blobs are removed as noise in order to refine the segmentation results. The proposed GPU-based image processing algorithms are implemented using the compute unified device architecture (CUDA) toolkit. The testing results show a significant enhancement in both speed and accuracy.