Support Vector Machines (SVMs) deliver stateof-the-art performance in real-world applications and are now established as one of the standard tools for machine learning and data mining. A key problem of these methods is how to choose an optimal kernel and how to optimise its parameters. The real-world applications have also emphasised the need to consider a combination of kernelsa multiple kernel-in order to boost the classification accuracy by adapting the kernel to the characteristics of heterogeneous data. This combination could be linear or non-linear, weighted or un-weighted. Several approaches have been already proposed to find a linear weighted kernel combination and to optimise its parameters together with the SVM parameters, but no approach has tried to optimise a non-linear weighted combination. Therefore, our goal is to automatically generate and adapt a kernel combination (linear or nonlinear, weighted or un-weighted, according to the data) and to optimise both the kernel parameters and SVM parameters by evolutionary means in a unified framework. We will denote our combination as a kernel of kernels (KoK). Numerical experiments show that the SVM algorithm, involving the evolutionary kernel of kernels (eKoK) we propose, performs better than well-known classic kernels whose parameters were optimised and a state of the art convex linear and an evolutionary linear, respectively, kernel combinations. These results emphasise the fact that the SVM algorithm could require a non-linear weighted combination of kernels.
In this paper different matching cost functions used for stereo matching are evaluated in the context of intelligent vehicles applications. Classical costs are considered, like: sum of squared differences, normalized cross correlation or census transform that were already evaluated in previous studies, together with some recent functions that try to enhance the discriminative power of Census Transform (CT). These are evaluated with two different stereo matching algorithms: a global method based on graph cuts and a fast local one based on cross aggregation regions. Furthermore we propose a new cost function that combines the CT and alternatively a variant of CT called Cross-Comparison Census (CCC), with the mean sum of relative pixel intensity differences (DIFFCensus). Among all the tested cost functions, under the same constraints, the proposed DIFFCensus produces the lower error rate on the KITTI road scenes dataset 1 with both global and local stereo matching algorithms.
The amount of health information available on the Internet is considerable.
Pedestrian detection is an important but challenging component of an Intelligent Transportation System. In this paper, we describe a pedestrian detection system based on a monocular vision with a Far-Infrared camera (FIR). We propose an original feature representation, called Intensity Self Similarity (ISS) , adapted to pedestrian detection in FIR images. The ISS representation is based on the relative intensity self similarity within a pedestrian region of interest (ROI) hypothesis. Our system consists of two components. The first component generates pedestrian ROI hypothesis by exploiting the specific characteristics of FIR images, where pedestrian shapes may vary in large scale, but heads appear usually as light regions. Pedestrian ROI are detected, with high recall rate, due to a Hierarchical Codebook (HC) of Speeded-Up Robust Features (SURF) located in light head regions. The second component consists of pedestrian hypothesis validation, by using a pedestrian full-body classification based on the ISS representation, with Support Vector Machine (SVM). For classification, we retained two feature descriptors: the Histogram of Oriented Gradients (HOG) descriptor and the original ISS feature representation that we proposed for FIR images. The early fusion of these two features enhances significantly the system precision, attaining an F-measure for the pedestrian class of 97.7%. Moreover, this feature fusion outperforms the state-of-the-art SURF descriptor proposed previously. The experimental evaluation shows that our pedestrian detector is also robust, since it performs well in detecting pedestrians even in large scale and crowded real-world scenes.
A great interest is focused on driver assistance systems using the head pose as an indicator of the visual focus of attention and the mental state. In fact, the head pose estimation is a technique allowing to deduce head orientation relatively to a view of camera and could be performed by model-based or appearance-based approaches. Modelbased approaches use a face geometrical model usually obtained from facial features, whereas appearance-based techniques use the whole face image characterized by a descriptor and generally consider the pose estimation as a classification problem. Appearance-based methods are faster and more adapted to discrete pose estimation. However, their performance depends strongly on the head descriptor, which should be well chosen in order to reduce the information about identity and lighting contained in the face appearance. In this paper, we propose an appearancebased discrete head pose estimation aiming to determine the driver attention level from monocular visible spectrum images, even if the facial features are not visible. Explicitly, we first propose a novel descriptor resulting from the fusion of four most relevant orientation-based head descriptors, namely the steerable filters, the histogram of oriented gradients (HOG), the Haar features, and an adapted version of speeded up robust feature (SURF) descriptor. Second, in order to derive a compact, relevant, and consistent subset of descriptor's features, a comparative study is conducted on some well-known feature selection algorithms. Finally, the obtained subset is subject to the classification process, performed by the support vector machine (SVM), to learn head pose variations. As we show in experiments with the public database (Pointing'04) as well as with our real-world sequence, our approach describes the head with a high accuracy and provides robust estimation of the head pose, compared to state-of-the-art methods.
The obstacle detection field is a very broad one and a lot of obstacle detection systems have been developed in the last years in this domain. We tried to identify the main character of an obstacle detection system from the ruttier scene. Thus, we classified the main types of sensors from this field in passive (visible and infrared spectrum camera) and active (radar, laser-scanner, sonar) sensors and we made a survey in this domain. After a short presentation of every type of sensor, we presented another current andfancy solution for an obstacle detection system. the fusion of different sensor together. Almost all obstacle detection systems use a combination ofpassive-active technology, and in general the best solution is obtained using a vision system combined with a distance sensor like radar or laser. Maybe the most low-priced system is one combining only vision systems, but the inconvenient in this case is the lack ofdistance information.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.