Vehicles detection for illumination changes urban traffic scenes employing adaptive local texture feature background model

Zhang, Yunsheng; Zhao, Chihang; Shi, Wen Zhong; Leng, Kaijun

doi:10.1049/iet-its.2018.5298

Cited by 3 publications

(3 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A new local binary similarity pattern (LBSP) [30] feature was proposed to handle the sensitivity of illumination changes. Our previous work [31] introduced an adaptive local texture feature (ALTF) to deal with sudden and gradual illumination changes using Weber's law and a sample consensus scheme. To address the illumination variation issue, a new spatial feature descriptor, which extracts the prominent directional information in the local neighborhood of a pixel, was introduced in [32].…”

Section: Compared With Histogram Of Oriented Gradients (Hog) Andmentioning

confidence: 99%

“…That is, all the compared models were reconstructed with a sample consensus scheme without pattern kernel density estimation or histogram approach. The ALMT feature of our model was replaced by LBP [22], LTP [26], SILTP [27], LBSP [30], LLSD [40], IIF [20] and ALTF [31] features to build corresponding LBP model (LBPM) , LTP model (LTPM), SILTP model (SILTPM), LBSP model (LBSPM), LLSD model(LLSDM), IIF model (IIFM) and ALTF model (ALTFM), respectively. Moreover, all the parameters of features in the compared methods were set to the optimum values according to the original authors' recommendations and the other parameters of consensus scheme method were set to the same value as in our model.…”

Section: Experiments a Experimental Datasets And Model Comparisonsmentioning

confidence: 99%

“…R and Th need to be adjusted in different environments to obtain the optimal performance, which is a challenging work. Therefore, employing several experiments in real-world urban traffic scenes, we empirically set 4 R Th  , as in our previous work [31]. For urban traffic scenes, the threshold value of the Hamming distance 4 R  and the minimum match threshold value 4 Th  are an excellent trade-off between noise resistance and accuracy of foreground detection.…”

Section: Bparameters Settingmentioning

confidence: 99%

See 2 more Smart Citations

Background Subtraction Using an Adaptive Local Median Texture Feature in Illumination Changes Urban Traffic Scenes

et al. 2020

Self Cite

View full text Add to dashboard Cite

Background subtraction is commonly employed in foreground object detection in urban traffic scenes. Most of the current color or texture feature-based background subtraction models are easily contaminated by sudden and gradual illumination variations in urban traffic scenes. To resolve this deficiency, an adaptive local median texture feature, which extracts the adaptive distance threshold employing the median information in a predefined local region of a pixel and Weber's law, is introduced. In addition, a sample consensus-based model that evolved from portable visual background extractor is proposed using an adaptive local median texture feature. Then, the foreground is labeled by comparing the input video frames feature with the model. Moreover, to adapt the dynamic background, the random update scheme is used to update the model. Extensive experimental results on the public Change Detection data set of 2014 (CDnet2014) and the real-world urban traffic videos demonstrate that our background subtraction method is superior to the other state-of-the-art texture-feature-based methods. The qualitative and quantitative results show the encouraging efficiency of the proposed technique to deal with sudden and gradual illumination variations in real-world urban traffic scenes. INDEX TERMS background modeling, illumination variations, local median texture feature, urban traffic scenes

show abstract

Section: Compared With Histogram Of Oriented Gradients (Hog) Andmentioning

confidence: 99%