Helmet presence classification with motorcycle detection and tracking

Motorcycle detection for ADAS through camera and V2V Communication, a comparative analysis of two modern technologies

“…However, this technology lacks of a lower field of view and it is strongly sensitive to occlusions. The use of the láser scanner, reduces the false positives which may arise due to the use of computer visión approaches, such as the presented in Tai and Song (2010), Chiverton (2012), Hall and Birchfield (2010) and Phatanasrirat and Phiphobmongkol (2009). On the other hand, the addition of computer visión approach, based on HOG features and SVM allows to provide vehicle detection, by means of a powerful visión technique, which proved great performance in previous works, such as García et al (2014).…”

“…Some of the works related to motorcycle detection rely on the detection of the helmet, prior or posterior to the detection of the motorcycle: Tai, Tseng, Lin, and Song (2004) and Tai and Song (2010) propose vision-based detection algorithms, relying in the helmet search and detection; in the former work, an automatic contour initialization method is used for vehicles and motorcycles tracking; in the latter, a further occlusion segmentation is presented. Chiverton (2012) presents a system for automatic classification and tracking of motorcycle riders, based on head detection (with or without helmet), relying in Support Vector Machines (SVM) algorithm, trained with histograms derived from head región image data. Background subtraction is later used for tracking.…”

Classification of Motorcyclists not Wear Helmet on Digital Image with Backpropagation Neural Network

“…Table 2 shows that the best accuracy is obtained on the results of training with a learning rate value of 0.2, 0.3, and 0.6 in the amount of 86.67%. Whereas the method of Support Vector Machines (SVM) was used for the same case with the average accuracy rate is 85% [7]. This accuracy level can be improved by increasing the number of training data because the performance of backpropagation neural network algorithm is affected by the amount of data variation that has been trained.…”

“…The result of the recording can be used for example to detect or to classify motorcyclist wearing a helmet or not automatically. Research from this classification issues has been done by using Support Vector Machines (SVM) to generate an accuracy rate of 85% [7]. This paper explains the classification process of motorcylists wearing a helmet and not on the highway on digital image with backpropagation neural network.…”

Video-based tracking of vehicles using multiple time-spatial images

“…In order to find the solution of the state-space model, the density function of the random processes can be chosen as parametric or non-parametric. The Kalman filter (KF)-based vehicle tracking is the most popular among the parametric approaches ( Chiverton, 2012;Shantaiya, Verma, & Mehta, 2015;Sivaraman & Trivedi, 2013 ), which obtains an analytical solution for tracking by assuming linear dynamics of vehicular movements and a Gaussian distributed intensity of vehicular objects ( Shalom, Li, & Kirubarajan, 2001 ). Due to the variations of traffic, weather or viewing conditions, the intensities of the vehicular objects may follow non-Gaussian statistics and the movements of vehicular objects may follow a non-linear dynamics.…”