Improved Haar Wavelet Feature Extraction Approaches for Vehicle Detection

Wen, Xuezhi; Yuan, Huai; Yang, Chunyang; Song, Chunyan; Duan, Bobo; Zhao, Hong

doi:10.1109/itsc.2007.4357743

Cited by 15 publications

(6 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Inspired by ideas in [39], Haar features are widely used for solving various object-detection problems (e.g., [22], [40]). The value of such a local feature is defined by a weighted difference of image values in white or black rectangular windows, efficiently calculated by using an integral image [41].…”

Section: A Global Haar Featuresmentioning

confidence: 99%

“…Regarding vision-based methodologies [12], current research addresses subjects such as vehicle detection based on analysing shadow underneath a vehicle [13], [14], stereo vision to estimate distances between the ego-vehicle (i.e., the car the system is operating in) and obstacles [15], [16], optical flow-based methods to detect moving objects and vehicles [17], application of local binary patterns (LBP) [18], [19], or of Haar-like features [20]- [22]. Haar-like features are named after the wavelets of the Haar transform [23], and hereafter we call them Haar features in this paper.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Robust Vehicle Detection and Distance Estimation Under Challenging Lighting Conditions

Rezaei

Terauchi

Klette

2015

IEEE Trans. Intell. Transport. Syst.

111

View full text Add to dashboard Cite

Avoiding high computational costs and calibration issues involved in stereo-vision-based algorithms, this paper proposes real-time monocular-vision-based techniques for simultaneous vehicle detection and inter-vehicle distance estimation, in which the performance and robustness of the system remain competitive, even for highly challenging benchmark datasets. This paper develops a collision warning system by detecting vehicles ahead and, by identifying safety distances to assist a distracted driver, prior to occurrence of an imminent crash. We introduce adaptive global Haar-like features for vehicle detection, tail-light segmentation, virtual symmetry detection, intervehicle distance estimation, as well as an efficient single-sensor multifeature fusion technique to enhance the accuracy and robustness of our algorithm. The proposed algorithm is able to detect vehicles ahead at both day or night and also for short-and long-range distances. Experimental results under various weather and lighting conditions (including sunny, rainy, foggy, or snowy) show that the proposed algorithm outperforms state-of-the-art algorithms.

show abstract

Section: A Global Haar Featuresmentioning

confidence: 99%

mentioning

confidence: 99%

Robust Vehicle Detection and Distance Estimation Under Challenging Lighting Conditions

Rezaei

Terauchi

Klette

2015

IEEE Trans. Intell. Transport. Syst.

111

View full text Add to dashboard Cite

show abstract

“…Global Haar Features. Following Viola and Jones [25], Haar features are widely used for solving various object detection problems (e.g., see [19,26]). The value of such a Haar feature is defined by a weighted difference of image values in white or black adjacent rectangular patches, efficiently calculated by using an integral image [3].…”

Section: Adaptive Global Haar Classifiermentioning

confidence: 99%

“…Vision-based driver assistance research addresses subjects such as vehicle detection based on analysing shadow underneath a vehicle [1,6], stereo vision to estimate distances between ego-vehicle (i.e. the car the system is operating in) and obstacles [24], optical flow-based methods [2], the utilization of local binary patterns (LBP) [15,17], or of Haar-like features [11,13,26].…”

Section: Introductionmentioning

confidence: 99%

Vehicle Detection Based on Multi-feature Clues and Dempster-Shafer Fusion Theory

Rezaei

Terauchi

2014

Image and Video Technology

View full text Add to dashboard Cite

On-road vehicle detection and rear-end crash prevention are demanding subjects in both academia and automotive industry. The paper focuses on monocular vision-based vehicle detection under challenging lighting conditions, being still an open topic in the area of driver assistance systems. The paper proposes an effective vehicle detection method based on multiple features analysis and Dempster-Shafer-based fusion theory. We also utilize a new idea of Adaptive Global Haar-like (AGHaar) features as a promising method for feature classification and vehicle detection in both daylight and night conditions. Validation tests and experimental results show superior detection results for day, night, rainy, and challenging conditions compared to state-of-the-art solutions.

show abstract

“…One subsignal is a running average or trend, the other subsignal is a running difference or fluctuation. The Haar wavelet transform has the advantages of being conceptually simple, fast and memory efficient, since it can be calculated in place without a temporary array [17]. Furthermore, it is exactly reversible without the edge effects that are a problem of other wavelet transforms.…”

Section: B Daubechies Waveletsmentioning

confidence: 99%

On the selection of the proper wavelet for moving object detection

Salem

2011

The 2011 International Conference on Computer Engineering &Amp; Systems

View full text Add to dashboard Cite

A precise event detection is a fundamental step in many applications. For instancs, moving object detection is a fundamental task for a variety of traffic monitoring applications. Wavelets have been widely used for this purpose. However, The selection of the proper type of mother wavelet strongly affects the results of the analysis and processing. In this paper, the wavelets of the Daubechies family are exploited for extracting the relevant movement information in mov ing image sequences using 3D wavelet. The proposed algorithm is applied for traffic monitoring systems. The objective and subjective experimental results obtained by applying the wavelet types are compared and in terpreted in terms of the wavelet properties and the characteristics of the image sequences. The compar isons show the superior performance of the low order Daubechies wavelets in the presence of noisy images and changing lighting conditions when compared to the application of high order Daubechies wavelets.

show abstract

Improved Haar Wavelet Feature Extraction Approaches for Vehicle Detection

Cited by 15 publications

References 11 publications

Robust Vehicle Detection and Distance Estimation Under Challenging Lighting Conditions

Robust Vehicle Detection and Distance Estimation Under Challenging Lighting Conditions

Vehicle Detection Based on Multi-feature Clues and Dempster-Shafer Fusion Theory

On the selection of the proper wavelet for moving object detection

Contact Info

Product

Resources

About