Adaptive shadow detection using global texture and sampling deduction

Jiang, Ke; Li, Aihua; Cui, Zhigao; Wang, Tao; Su, Yanzhao

doi:10.1049/iet-cvi.2012.0106

Cited by 20 publications

(10 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the existence of the shadow will lead to false detection, which will cause a large error count of vehicles. Common shadow detection methods are based on texture and SNP shadow detection algorithm [12], however, the two can only be in a specific environment to have a better effect of shadow detection.…”

Section: Vehicle Detection and Shadow Eliminationmentioning

confidence: 99%

Research on Traffic Monitoring Method of Elevated Road Based on DSP+FPGA

Chen

Fei²,

Xiao

et al. 2017

Proceedings of the 3rd International Conference on Wireless Communication and Sensor Networks (WCSN 2016)

View full text Add to dashboard Cite

This paper has obtained the taxi speed through the high road video monitoring system to determine whether the elevated road is congested. A scheduling method is proposed to preclude overhead road congestion in advance. The existing video monitoring system is used as base. The vehicle is extracted by means of motion target detection. The type of vehicle is distinguished by the Hu invariant moment. The vehicle is divided into color and non-color through HSL (Hue Saturation and Lightness) space. The centroid location of the color vehicle is carried out and the color recognition of the matrix in the centroid range is used to judge whether the vehicle has a dome light. If the vehicle is a taxi, measure the speed of the taxi. Traffic congestions in the viaduct is deemed to occur soon if the taxi speed is obviously lower. Relevant measures shall be taken immediately to eliminate the possibility of congestion and ensure the normal use of viaduct. Because of the complexity of traffic congestion, the process of removing congestion is very difficult. Predicting the occurrence of traffic congestion and scheduling can alleviate this contradiction. Meanwhile it improves the intelligent property of video surveillance system and saves social resources.

show abstract

Section: Vehicle Detection and Shadow Eliminationmentioning

confidence: 99%

Research on Traffic Monitoring Method of Elevated Road Based on DSP+FPGA

Chen

Fei²,

Xiao

et al. 2017

Proceedings of the 3rd International Conference on Wireless Communication and Sensor Networks (WCSN 2016)

View full text Add to dashboard Cite

show abstract

“…Algorithms in which the color features of video frame are used are the first group of this basic classification. Color spaces such as HSV [13], nRGB [14] and Yuv [15] maintain superiority compared to other color spaces in detection of shadow regions. There are some other shadow detection algorithms presented in the literature that take the physical features of the shadow along with its color features as the basis.…”

Section: Shadow Detetion Algorithmmentioning

confidence: 99%

A shadow detection approach based on fuzzy logic using images obtained from PV array

Karaköse

Firildak

2015

2015 6th International Conference on Modeling, Simulation, and Applied Optimization (ICMSAO)

View full text Add to dashboard Cite

Shadows on PV arrays influence the energy production performance negatively. There are many methods in the literature related to the detection of these shadows and reconfiguration of arrays. The methods proposed in the literature generally aim at reconfiguration of arrays and detecting shadow regions by using current (I), voltage (V) and power (P) information. In the process of reconfiguration it is quite difficult to measure to use P, V, I information. In this paper, in order to use in the reconfiguration processes for the detection of the shadow region on PV arrays, a new fuzzy logic based computer vision method is presented. The proposed method, firstly, performs object detection with background subtraction. Then, detects the edge of the object regions. Finally, it detects shadow regions with the help of fuzzy logic decision making system. Experimental results are provides effective performance for detecting of shaded areas on PV arrays.

show abstract

“…Information of color, shading, texture, neighborhood and temporal consistency are used to detect shadows efficiently and adaptively in [26]. Jiang et al [13] uses three components in YUV color space to identify shadow pixels from the candidate foreground. An adaptive threshold estimator is designed using edges to improve shadow detection accuracy and adaptive capacity in various lighting conditions.…”

Section: Related Workmentioning

confidence: 99%

Online sequential extreme learning machine-based co-training for dynamic moving cast shadow detection

Ghimire

Lee

2015

Multimed Tools Appl

View full text Add to dashboard Cite

Cast shadow detection and removal is one of the key problems in vision-based systems for accurate and robust segmentation of moving objects. This paper proposes a cotraining-based adaptive method for detecting moving shadows in video sequences. Shadow detection based on static methods cannot adapt to changing environment such as gradual illumination changes. In order to solve this problem, we have proposed an online sequential extreme learning machine (OS-ELM)-based semi-supervised technique for moving cast shadow detection. Online learning of OS-ELM is much faster and provides better generalization performance compared to other popular online learning algorithms. First, we extracted color, texture, gradient, and image patch similarity features using a background model and input video frame, which are useful for discriminating moving shadows and objects. Co-training scheme is used for online updating of the OS-ELM classifier in order to adapt to the dynamic environment. Experimental results on different benchmark video sequences shows that the proposed method performs better shadow detection and discrimination compared with other methods.

show abstract

Adaptive shadow detection using global texture and sampling deduction

Cited by 20 publications

References 41 publications

Research on Traffic Monitoring Method of Elevated Road Based on DSP+FPGA

Research on Traffic Monitoring Method of Elevated Road Based on DSP+FPGA

A shadow detection approach based on fuzzy logic using images obtained from PV array

Online sequential extreme learning machine-based co-training for dynamic moving cast shadow detection

Contact Info

Product

Resources

About