Vision-based bicycle/motorcycle classification

Messelodi, Stefano; Modena, Carla Maria; Cattoni, G.

doi:10.1016/j.patrec.2007.04.014

Cited by 44 publications

(28 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This method requires various orientation images of the same vehicle for effective classification which might lead to a huge and redundant training data set. Messelodi et al [17] presents a novel way of classifying bicycles and motorcycles by extracting the features from the wheel region of the vehicles and using a SVM classifier, but such specific features are not an efficient way to classify vehicles.…”

Section: Literature Reviewmentioning

confidence: 99%

Vehicle Classification using Density based Multi-feature Approach in Support Vector Machine Classifier

Mishra

Banerjee²

2013

IJCA

View full text Add to dashboard Cite

A density based multi-feature combination approach to classify vehicles using support vector machine (SVM) classifier is proposed in this paper. Features like Haar, Gradient, RGB and Pyramidal histogram of oriented gradients are extracted from vehicle images and a kernel density approximation is performed. The results are compared with another set of multi-feature combination and effects of using kernel density estimators and various kernels like Gaussian, Polynomial and Histogram intersection in SVM are also studied. It is found that the above mentioned feature combination produces good results in comparison and effects of scaling, orientation and shadowing were properly compensated. A sample set of 9360 images were used with half of them used for training the classifier and the other half for testing. The vehicles were clustered into four categories, namely 2-wheeler, 3-wheeler, light motor vehicle (LMV) and heavy motor vehicles (HMV) and an accuracy greater than 90% has been observed.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Vehicle Classification using Density based Multi-feature Approach in Support Vector Machine Classifier

Mishra

Banerjee²

2013

IJCA

View full text Add to dashboard Cite

show abstract

“…There are two main categories of static features: texture-and gradient-based descriptors. The texture descriptor includes the wavelets-based feature [5], [10] and the local binary pattern (LBP) [11]- [13] that finds a histogram of the labels assigned to each pixel considering its neighboring pixels, among others. The gradient-based descriptor employs derivative masks to obtain gradients of each pixel based on which local features are extracted.…”

Section: Introductionmentioning

confidence: 99%

Moving Object Classification Using a Combination of Static Appearance Features and Spatial and Temporal Entropy Values of Optical Flows

Liang

Juang

2015

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

This paper proposes a new approach for classifying four types of moving objects in an intelligent transportation system. Pedestrians, cars, motorcycles, and bicycles are classified based on their side views from a fixed camera. A moving object is segmented and tracked using background subtraction, silhouette projection, an area ratio, a Kalman filter, and appearance correlation operations. For the classification of a segmented object, a combination of static and spatiotemporal features based on the cooccurrence of its appearance and the movements of its local parts is proposed. To extract the static appearance features, adaptive block-based gradient intensities and histograms of oriented gradients are proposed. For the spatiotemporal features, the optical-flow-based entropy values of instantaneous and short-term movements are proposed. The former finds the spatial entropy values of the orientations and the amplitudes of optical flows in a block to extract the local movement information from two consecutive image frames. The latter finds the temporal entropy values of the tracked optical flows in different orientation bins to extract the short-term movement information from several consecutive frames. Linear support vector machines with batch incremental learning are proposed to classify the four classes of objects. Experimental results from 12 test video sequences and comparisons with several feature descriptors show the effect of the proposed classification system and the advantage of the proposed features in classification. coauthor of 7 book chapters, over 90 journal papers (including over 50 IEEE journal papers), and over 90 conference papers. His current research interests include computational intelligence (CI), the chip implementation of CI techniques, intelligent control, computer vision, and evolutionary robots.Dr.

show abstract

“…Though it is possible to connect a movement sensor with a camera and make an image analysis, the obtained results -unlike those for the detection of motor vehicles -have so far been unsatisfactory for the monitoring of cycling. There have been promising attempts to distinguish cyclists and motorcyclists (MESSELODI et al, 2007), however similarly to the video detection of cyclists and pedestrians (HEIKKILA and SILVÉN, 2004), they do not yet have commercial applications.…”

Section: Introductionmentioning

confidence: 99%

Use of Palmtop Computers for Monitoring Traffic

Bíl¹,

Bílová²,

Martinek³

2009

ToTS

View full text Add to dashboard Cite

On the basis of a cycling traffic count carried out in the town of Olomouc a new method of monitoring traffic was presented based on the use of palmtop computers (PDAs). For short-term traffic counts, this method may entirely replace the commonly used paper forms. In addition, this method provides more possibilities, namely the recording of the exact time of vehicle passing and a description of the direction of vehicle movement. Almost all the software used for the preparation and processing of data is freely available, which allows all interested people to use this method.

show abstract

Vision-based bicycle/motorcycle classification

Cited by 44 publications

References 4 publications

Vehicle Classification using Density based Multi-feature Approach in Support Vector Machine Classifier

Vehicle Classification using Density based Multi-feature Approach in Support Vector Machine Classifier

Moving Object Classification Using a Combination of Static Appearance Features and Spatial and Temporal Entropy Values of Optical Flows

Use of Palmtop Computers for Monitoring Traffic

Contact Info

Product

Resources

About