The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
An approach for keyframe extraction using AdaBoost is proposed which is based on foreground detection. The aim of this approach is to extract keyframes from sequences of specific vehicle images of lane vehicle surveillance video. This method utilizes integral channel features and the area feature as the image feature descriptor, combined with training an AdaBoost classifier. The experimental results...
In the modern battlefield scenario multiple sources of information may be exploited to mitigate uncertainty. Polarization and spatial diversity can provide useful information for specific and critical tasks such as the Automatic Target Recognition (ATR). In this paper the use of pseudo-Zernike moments applied to the full-polarimetric Gotcha dataset is presented. Specifically improved single platform...
In this paper we present a method for roadside vegetation detection from video obtained from a moving vehicle with intended use in road infrastructure maintenance and traffic safety. While many published methods are using Near Infrared images which are suitable for vegetation detection, our method uses image features from the visible spectrum allowing the use of a common color camera. The presented...
This paper presents a vision-based solution for detection and tracking of convoy vehicles. Our approach is able to estimate the 3D vehicle pose, velocity and steering angle of the leader vehicles and needs template images of each vehicle. The improved template-based algorithm refers to a previously publication. First, we present an extension of our dynamic region growing algorithm, which is used to...
The goal of the project is to design intelligent and robust image-processing and augmented-reality algorithms for driver assistance and enhanced vehicular safety. In particular, the focuses were two-fold: (1) realizing the abilities to identify and localize in a vehicle''s on-board video the sweeping windshield wipers during raining days and (2) designing and implementing an in-painting technique...
A fuzzy rule-based and energy-efficient method for estimating the free size of parking places in smart cities is proposed. In particular, the estimation is the output value of a fuzzy inference system (FIS) which was implemented on each wireless sensor mote (WSM) of a wireless sensor network (WSN) placed in the ground below the parking places and it was observed that it requires 8.9 Kbytes and 5 Kbytes...
Deviation detection is important for self-monitoring systems. To perform deviation detection well requires methods that, given only "normal" data from a distribution of unknown parametric form, can produce a reliable statistic for rejecting the null hypothesis, i.e. evidence for devating data. One measure of the strength of this evidence based on the data is the p-value, but few deviation...
Despite many years of research, pedestrian recognition is still a difficult, but very important task. We present a multi-modality approach, that combines features extracted from three type of images: intensity, depth and flow. For the feature extraction phase we use Kernel Descriptors, which are optimised independently on each type of image, and for the learning phase we use Support Vector Machines...
In this paper, we present a novel interface for teleoperating ground vehicles. Obstacle avoidance with ground vehicles demands a high level of operator attention, typically distracting from the primary mission. The Ambient Obstacle Avoidance (AOA) was designed to allow operators to effectively perform a primary task, such as search, while still effectively avoiding obstacles. The AOA wraps around...
A vehicle detection system is realized in two stages: hypothesis generation (HG) and hypothesis verification (HV). HG adopts frame division and shadow detection to find possible candidates of vehicles within a plausible region of the image frame. Then, during HV, object ratio constraint is first used to eliminate unreasonable hypotheses. Afterward, based on the training results of the support vector...
In this paper, we investigated the deep learning model for object classification. Robust classification networks were trained based on Deep Belief Networks (DBN) combined with several object representations included image pixel value, feature histogram by Histogram of Oriented Gradients (HOG) operator and eigen-features to distinguish four categories: pedestrian, biker, vehicle and others in the real...
With the dramatic growth of using video cameras for applications of public surveillances in recent years, detection of public threats or security issues on surveillances becomes possible nowadays. How to identify anomalous behavior from surveillance videos has been identified as an effective manner for detecting critical events in the public avenue. We in this paper discuss a new application paradigm...
In this paper, we propose a novel dynamic ensemble selection framework using meta-learning. The framework is divided into three steps. In the first step, the pool of classifiers is generated from the training data. The second phase is responsible to extract the meta-features and train the meta-classifier. Five distinct sets of meta-features are proposed, each one corresponding to a different criterion...
Traffic congestion judgement is a frequently addressed problem in intelligent transportation system. In this paper, a judgement algorithm for identifying the occurring traffic congestion of vehicles is experimentally designed. This algorithm extracts the SIFT features from an image containing vehicles using the linear spatial pyramid matching using sparse coding (ScSPM), then judges wether the congestion...
In this paper, we propose a method for estimating, from the vehicle behavior, a target driver's awareness of pedestrians that are crossing or are about to cross a pedestrian crosswalk on the driver's left while the driver is poised to turn left at a target intersection (left-hand traffic is supposed). To construct such an estimation model based on statistical learning, a large number of training examples...
The designing based on Adaboost algorithm not only achieved the nighttime pedestrian detection module of auxiliary driving system, but also realized the system optimization on issues of low detection speed and precision. In this design, variable step length and partition scanning track methods are used to improve the detection speed and variance normalization approach was applied to eliminate the...
The purpose of this study is to increase the face detection accuracy in vehicle cabin. Although existing face detectors employed in consumer applications already have sufficient face detection accuracy for many situations, we revealed that detection rate of existing face detector is drastically decreased by shadow on the driver's face caused by sunlight whose relative direction to the driver is continuously...
This paper introduces the new concept of discriminative auto encoders. In contrast with the standard auto encoders - which are artificial neural networks used to learn compressed representation for a set of data - discriminative auto encoders aim at learning low-dimensional discriminant encodings using two classes of data (denoted such as the positive and the negative classes). More precisely, the...
In this paper, we present a novel framework for representation of images as a combination of multiple mid-level feature descriptor representation based group of visual words. The mid-level feature representation is computed on discriminative patches of the image to build a lexicon, the visual words of which are used to represent the shape within that image. The proposed image representation method...
Practical surveillance systems deployed in urban scenarios need to operate 24/7 under a wide range of environmental conditions. As modern video analytics shift from blob-based to object-centered architectures, appearance-based object detection under different weather conditions and lighting effects emerges as a critical yet largely unaddressed problem. This paper investigates this research topic,...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.