Robust vehicle detection and identification is required for the intelligent persistent surveillance systems. In this paper, we
present a Multi-attribute Vehicle Detection and Identification technique (MVDI) for detection and classification of
stationary vehicles. The proposed model uses a supervised Hamming Neural Network (HNN) for taxonomy of shape of
the vehicle. Vehicles silhouette features are employed for the training of the HNN from a large array of training vehicle
samples in different type, scale, and color variation. Invariant vehicle silhouette attributes are used as features for
training of the HNN which is based on an internal Hamming Distance and shape features to determine degree of
similarity of a test vehicle against those it’s selectively trained with. Upon detection of class of the vehicle, the other
vehicle attributes such as: color and orientation are determined. For vehicle color detection, provincial regions of the
vehicle body are used for matching color of the vehicle. For the vehicle orientation detection, the key structural features
of the vehicle are extracted and subjected to classification based on color tune, geometrical shape, and tire region
detection. The experimental results show the technique is promising and has robustness for detection and identification
of vehicle based on their multi-attribute features. Furthermore this paper demonstrates the importance of the vehicle
attributes detection towards the identification of Human-Vehicle Interaction events.

A multi-attribute based methodology for vehicle detection and identification

Feature extraction plays a key role in pattern recognition problems. The texture feature is an important feature which helps to describe an image with textural information. A new texture descriptor...

Texture classification using the rotational-invariant local symmetric tetra pattern

The purpose of this paper is real time forest fire detection system on changing of the background and the foreground. This study is focused on easy case between Hardware and software, and made up widely used methods as a basis for each step. First step is a process for detecting targeted forest fire by using HSV color space. On second step, adaptive threshold used for more accurate and intuitive representation on forest fire area. And third step labeling used for distinguishing the target area. Final step, histogram back-projection used for processing exception situation. By using proposed a method in this study, stable operation and more reliable method is prove by simple experiments on detecting of the foreground.

/pdf/a-simplified-forest-fire-detection-system-and-improved-area-k8sdru4c84.pdf

A Simplified Forest Fire Detection System and Improved Area Detection Method for Handling Exception

This paper presents a recognition method for natural images based on color texture histograms in the context of image interpretation and scene modeling. A color histogram of sums and differences is proposed to obtain texture features which are faster to compute than correlograms ( i.e., colored version of co-occurrence matrices) and improving substantially object recognition. Outdoor natural images are generally affected by color casting artifacts which can affect object recognition. Therefore, an on-line color balancing algorithm based on chromatic adaptation models, eliminates these color deviations. The proposed approach globally involves functions as color segmentation, histogram texture analysis and a region recognition step. Our approach has been extensively tested and validated to obtain an accurate 2D scene interpretation from natural images. This technique may be used in robot navigation by identifying navigable regions ( e.g., roads or fairly flat surfaces) on natural scenes, scene modeling and image categorization.

Color Texture Histograms for Natural Images Interpretation

This paper presents the development of a fuzzy control implemented in a domestic refrigerator in which the thermal load (food) is included as an input variable and a novel aspect of the control. The fuzzy control regulates the speed of the fan attached to the evaporator and the airflow to the fresh food compartment of the refrigerator according to a set of rules that incorporate the amount of thermal load and the temperature conditions of the compartments. The fuzzy control was evaluated in an empty refrigerator (without food) and with three thermal load conditions. Thus, resulting in a fuzzy control capable of maintaining thermal conditions similar to those obtained with the factory ON/OFF refrigerator controller. In addition, the total energy consumption is reduced by 1.7% when the refrigerator is empty and by a maximum of 9.53% in the presence of a low thermal load. Finally, the coefficient of performance shows increases in all the cases studied with the implementation of the fuzzy control. 

D. Hernandez-Fusilier

Papers

Color Texture Histograms for Natural Images Interpretation

Implementation of fuzzy control in a domestic refrigerator considering the influence of the thermal load