Contour extraction of moving objects in complex outdoor scenes

WiTransformer: A Novel Robust Gesture Recognition Sensing Model with WiFi

The past decade has demonstrated the potential of human activity recognition (HAR) with WiFi signals owing to non-invasiveness and ubiquity. Previous research has largely concentrated on enhancing precision through sophisticated models. However, the complexity of recognition tasks has been largely neglected. Thus, the performance of the HAR system is markedly diminished when tasked with increasing complexities, such as a larger classification number, the confusion of similar actions, and signal distortion To address this issue, we eliminated conventional convolutional and recurrent backbones and proposed WiTransformer, a novel tactic based on pure Transformers. Nevertheless, Transformer-like models are typically suited to large-scale datasets as pretraining models, according to the experience of the Vision Transformer. Therefore, we adopted the Body-coordinate Velocity Profile, a cross-domain WiFi signal feature derived from the channel state information, to reduce the threshold of the Transformers. Based on this, we propose two modified transformer architectures, united spatiotemporal Transformer (UST) and separated spatiotemporal Transformer (SST) to realize WiFi-based human gesture recognition models with task robustness. SST intuitively extracts spatial and temporal data features using two encoders, respectively. By contrast, UST can extract the same three-dimensional features with only a one-dimensional encoder, owing to its well-designed structure. We evaluated SST and UST on four designed task datasets (TDSs) with varying task complexities. The experimental results demonstrate that UST has achieved recognition accuracy of 86.16% on the most complex task dataset TDSs-22, outperforming the other popular backbones. Simultaneously, the accuracy decreases by at most 3.18% when the task complexity increases from TDSs-6 to TDSs-22, which is 0.14-0.2 times that of others. However, as predicted and analyzed, SST fails because of excessive lack of inductive bias and the limited scale of the training data.

Multichannel concat-fusional convolutional neural networks

Because of the advantages of deep learning and information fusion technology, it has drawn much attention for researchers to combine them to achieve target recognition, positioning, and tracking. However, when the existing neural network process multichannel images (e.g., color images), multiple channels as a whole input into neural networks, which makes it hard for networks to fully learn information in R, G, and B channels of images. Therefore, it is not conducive to the final learning effect of the networks. To solve the problem, using different combinations of R, G, and B channels of color images for feature-level fusion, this paper proposes three fusion types as “R/G/B”, “R+G/G+B/B+R”, and “R+G+B/R+G+B/R+G+B” multichannel concat-fusional convolutional neural networks. Experimental results show that multichannel concat-fusional convolutional neural networks with fusional types of “R+G/G+B/B+R” and “R+G+B/R+G+B/R+G+B” achieve better performance than the corresponding non-fusional convolutional neural networks on different datasets. It shows that networks with fusion types of “R+G/G+B/B+R” and “R+G+B/R+G+B/R+G+B” can learn more fully information of R, G, and B channels of color images and improve the learning performance of networks.

A block-wise frame difference method for real-time video motion detection

This article proposes a motion detection method for real-time video analysis. It is the fundamental principle that the parts of the moving objects and the local changes of the images captured by static cameras are strongly correlated. Peak signal-to-noise ratio calculated in a block can characterize the significance of the changes in this area. Moving objects can therefore be detected by thresholding the peak signal-to-noise ratio of the blocks between two adjacent frames. The block-wise scheme used in this frame difference method can explore the local correlation of the movement in both space and time domains. This approach is robust to analyze the video images with noise and high variance caused by environmental changes, such as illuminations changes. Compared with other methods, the proposed method can achieve relatively high detection accuracy with less computation time, where real-time motion detection is available. Experimental results show that the proposed method cost averagely 50% of the running time of ViBe with 3.5% increase of the F-score on detection accuracy.

Video-Based Classification of Driving Behavior Using a Hierarchical Classification System with Multiple Features

Driver fatigue and inattention have long been recognized as one of the main contributing factors in traffic accidents. Therefore, the development of intelligent driver assistance systems, which provides automatic monitoring of driver's vigilance, is an urgent and challenging task. This paper presents a novel system for video-based driving behavior recognition. The fundamental idea is to monitor driver's hand movements and to use these as predictors for safe/unsafe driving behavior. In comparison to previous work, the proposed method utilizes hierarchical classification and treats driving behavior in terms of a spatio-temporal reference framework as opposed to a static image. The approach was verified using the Southeast University Driving-Posture Dataset, a dataset comprised of video clips covering aspects of driving such as: normal driving, responding to a cell phone call, eating and smoking. After pre-processing for illumination variations and motion sequence segmentation, eight classes of behavior were identified. The overall prediction accuracy obtained using the proposed approach was [Formula: see text] when using a hierarchical classification approach. The proposed approach was able to clearly identify two dangerous driving behaviors, Responding to a cellphone call and Eating, with recognition rates of 92.39% and 92.29% respectively.

DETECTION OF TRACKS IN AERIAL PHOTOS BY THE GIBBS SAMPLER

A problem of automatic detection of tracks in aerial photos is considered. We adopt a Bayesian approach and base our inference on an a priori knowledge of the structure of tracks. The probability of a pixel to belong to a track depends on how the pixel gray level differs from the gray levels of pixels in the neighborhood and on additional prior information. Several suggestions on how to formalize the prior knowledge about the shape of the tracks are made. The Gibbs sampler is used to construct the most probable configuration of tracks in the area. The method is applied to aerial photos with cell size of 1 sq. m. Even for detection of trails of width comparable with or smaller than the cell size, positive results can be achieved.

Figure-ground segmentation from occlusion

Layered video representations are increasingly popular; see [2] for a recent review. Segmentation of moving objects is a key step for automating such representations. Current motion segmentation methods either fail to segment moving objects in low-textured regions or are computationally very expensive. This paper presents a computationally simple algorithm that segments moving objects, even in low-texture/low-contrast scenes. Our method infers the moving object templates directly from the image intensity values, rather than computing the motion field as an intermediate step. Our model takes into account the rigidity of the moving object and the occlusion of the background by the moving object. We formulate the segmentation problem as the minimization of a penalized likelihood cost function and present an algorithm to estimate all the unknown parameters: the motions, the template of the moving object, and the intensity levels of the object and of the background pixels. The cost function combines a maximum likelihood estimation term with a term that penalizes large templates. The minimization algorithm performs two alternate steps for which we derive closed-form solutions. Relaxation improves the convergence even when low texture makes it very challenging to segment the moving object from the background. Experiments demonstrate the good performance of our method.

Automatic gait recognition via statistical approaches for extended template features

A gait recognition system using extended template features is presented. A proposed statistical approach is applied for feature extraction from spatial and temporal templates. This method can be used to reduce data dimensionality and to optimize the class separability of different gait sequences simultaneously. Dimensionality reduction is achieved by template extraction followed by principal component analysis. Gait recognition is achieved in the canonical space using a measure of accumulated distance as the metric. By incorporating spatial and temporal information into an extended feature, gait recognition becomes more robust and accurate than using spatial or temporal features alone.