Search

Object detection is a significant step of intelligent surveillance. The existing methods achieve the goals by technically designing or learning special features and detection models. Conversely, we propose an effective method for accurate object detection, which is inspired by the mechanism of memory and prediction in our brain. Firstly, a fix-sized window is slid on a static image to generate an image sequence. Then, a convolutional neural network extracts a feature sequence from the image sequence. Finally, a long short-term memory receives these sequential features in proper order to memorize and recognize the sequential patterns. Our contributions are 1) a memory-based classification model in which both of feature learning and sequence learning are integrated subtly, and 2) a memory-based prediction model which is specially designed to predict potential object locations in the surveillance scenes. Compared with some state-of-the-art methods, our method obtains the best performance in term of accuracy on three surveillance datasets. Our method may give some new insights on object detection researches. [ABSTRACT FROM AUTHOR]

Abstract: On minor component analysis (MCA) neural networks, a new algorithm is proposed. It is a self-stabilizing MCA algorithm, which means that the sign of the temporal change of the weight vector length is independent of the presented input vector. Algorithms without this property may suffer fluctuations and divergence. With suitable conditions on the initial weight vector and learning rate, a rigorous global convergence proof is given. The techniques used in the proof will be useful in many research issues such as independent component analysis, principle component analysis, etc. [Copyright &y& Elsevier]

Recently many promising results have been shown on face recognition related problems. However, age-invariant face recognition and retrieval remains a challenge. Inspired by the observation that age variation is a nonlinear but smooth transform and the ability of auto-encoder network to learn latent representations from inputs, in this paper, we propose a new neural network model called coupled auto-encoder networks (CAN) to handle age-invariant face recognition and retrieval problem. CAN is a couple of two auto-encoders which bridged by two shallow neural networks used to fit complex nonlinear aging and de-aging process. We further propose a nonlinear factor analysis method to nonlinearly decompose one given face image into three components which are identity feature, age feature and noise, where identity feature is age-invariant and can be used for face recognition and retrieval. Experiments on three public available face aging datasets: FGNET, CACD and CACD-VS show the effectiveness of the proposed approach. [ABSTRACT FROM AUTHOR]

Abstract: In this paper, the problem on an unique equilibrium solution of the bidirectional associative memory neural networks with distributed time-varying delays is investigated via Lyapunov stability theory. By using topological degree theory and M-matrix theory, several sufficient conditions ensuring the existence, uniqueness and global asymptotic stability of equilibrium solution are derived. An illustrative example is given to demonstrate the effectiveness of the obtained results. [Copyright &y& Elsevier]

• An Attention Guided Neural Network Models is proposed for occlusion handling in pedestrian detection. • Class activation mapping technique is implemented as the spatial attention mechanism. • Two different attention mechanisms have been explored. • The proposed model achieves a state-of-art performance in occluded pedestrian detection. Occluded pedestrian detection has been a research difficulty in computer vision for a long time. The conventional approach to solve this problem is to learn partial detectors, which can be properly integrated for occlusion handling. However, the efficiency of this type of methods is limited in practical applications since the partial detectors can not cover all occlusion patterns. In this paper, an attention guided neural network model (AGNN) is proposed for the occlusion handling of pedestrian detections, which is inspired by the approaches of sentiment classification. Firstly, a fixed-size window slides on a still image without overlapping to generate a set of sub-images. Secondly, a convolutional neural network is employed to extract the high-level features from resulting sub-images. Then, the attention network performs local feature weighting, from which the features representing the body parts of pedestrians are selected. Finally, the feature sequences are classified by recurrent neural network in proper order based on the weighted results. In addition, we explore different mechanisms of attention guidance on the detector for the detections. Compared with the state-of-the-art methods on two standard pedestrian datasets, experimental results demonstrate the comparable performance of our approach in terms of miss rates. [ABSTRACT FROM AUTHOR]

As an effective way for crowd control and management, crowd density estimation is an important research topic in artificial intelligence applications. Since the existing methods are hard to satisfy the accuracy and speed requirements of engineering applications, we propose to estimate crowd density by an optimized convolutional neural network (ConvNet). The contributions are twofold: first, convolutional neural network is first introduced for crowd density estimation. The estimation speed is significantly accelerated by removing some network connections according to the observation of the existence of similar feature maps. Second, a cascade of two ConvNet classifier has been designed, which improves both of the accuracy and speed. The method is tested on three data sets: PETS_2009, a Subway image sequence and a ground truth image sequence. Experiments confirm the good performance of the method on the same data sets compared with the state of the art works. [ABSTRACT FROM AUTHOR]

Abstract: The problem of robust exponential stability for a class of discrete-time recurrent neural networks with time-varying delay is investigated. By constructing a new augmented Lyapunov–Krasovskii functional, some new delay-dependent stable criteria are obtained. These criteria are formulated in the forms of linear matrix inequality (LMI). Compared with some previous results, the new conditions obtained in this paper are less conservative. Three numerical examples are provided to demonstrate the less conservatism and effectiveness of the proposed method. [Copyright &y& Elsevier]