Intelligent Autonomous Systems increasingly often operate in environments inhabited by humans, like houses, public places (stations, shopping centers) or intelligent vehicles. In order to properly interact with people an intelligent system has to detect people in its environment, identify them and possibly recognize their behavior. Examples of such systems are intelligent security systems that ...

With the development of intelligent operation and maintenance substations, daily inspection substations needs to process massive video image data. This puts forward higher requirements on processing speed accuracy defect detection. Based end-to-end learning paradigm, this article proposes an detection method for substation insulator defects based CenterMask. First, backbone network VoVNet is im...

The high pace rise in vehicle counts, traffic density, and security concerns, a potential system for traffic surveillance, vehicle monitoring and control has become an inevitable need to facilitate intelligent transportation system (ITS). Although, numerous approaches have been proposed for moving vehicle detection and tracking, still the optimization needs can’t be ignored. In this paper, a ro...

The license plate recognition system is part of the intelligent transportation system. In the intelligent transportation system, the vehicle image is used as the system input. The first step is to improve the image, after the edge detection, a series of morphological operations are performed to identify the plaque. The main purpose of this research was to increase the importance of plate re...

Abstract Anomaly detection aims to detect abnormal samples from normal data. Existing methods mainly use synthesis-based approach and uncertainty-based approach. Moreover, the above-mentioned need re-train part/all of deep network, which limits its application scenarios especially real-time scenarios. We propose a novel retraining-free anomaly method, includes dual-branch mechanism pixels two v...

In this paper, we present an edge detection method based on wavelet transform and Hessian matrix of image at each pixel. Many methods which based on wavelet transform, use wavelet transform to approximate the gradient of image and detect edges by searching the modulus maximum of gradient vectors. In our scheme, we use wavelet transform to approximate Hessian matrix of image at each pixel, too. ...

in this paper, we present an edge detection method based on wavelet transform and hessian matrix of image at each pixel. many methods which based on wavelet transform, use wavelet transform to approximate the gradient of image and detect edges by searching the modulus maximum of gradient vectors. in our scheme, we use wavelet transform to approximate hessian matrix of image at each pixel, too. ...

The edge detection model based on deep learning significantly improves performance, but its generally high complexity requires a large pretrained Convolutional Neural Networks (CNNs) backbone, and hence memory computing power. To solve this problem, we carefully choose proper components for detection, introduce Multiscale Aware Fusion Module self-attention feature-unmixing loss function, propos...