Human action recognition is an important research topic in the field of computer vision due to its application values. Recently, a variety of approaches based on deep learning features have been proposed due to the effectiveness of deep neural networks. But most of these approaches are not able to fully extract spatiotemporal features from videos, because of the lack of consideration of the diversity of scales in temporal domain. In this paper, we propose a two-stream convolutional network with long-short-term spatiotemporal features (LSF CNN) for human action recognition task. The network is mainly composed of two subnetworks. One is long-term spatiotemporal features extraction network (LT-Net) that takes the stacked RGB images as inputs. Another one is short-term spatiotemporal features extraction network (ST-Net) that takes the optical flow as input, which is estimated from two adjacent frames. The two-scale spatiotemporal features are fused in the fully-connected layer and fed into the linear support vector machine (SVM). We also propose a new expression for optical flow field, which is proved to have better performance than traditional expression in action recognition problem. With two-stream architecture, the network can fully learn deep features in both spatial and temporal domains. The experimental results on HMDB51 and UCF101 datasets indicated that the proposed approach improves the action recognition accuracy by using the long-short-term spatiotemporal information.

No abstract

In modern railway systems, video surveillance and machine vision analysis have been widely used to detect perimeter intrusions. For pan-tilt-zoom (PTZ) cameras, the machine vision system needs to detect adjustments in PTZ cameras and then automatically determine the new alarm region in real time. In this paper, we propose a deep multi-task learning based algorithm for simultaneous vanishing point (VP) detection and rail segmentation, which can identify camera adjustment from changes in VP, and then automatically determine the alarm region from segmented rails. The multi-task based neural network consists of a feature extraction base network and three sub-task networks. The first sub-task network is a convolution regression network for VP detection. The second sub-task network utilizes an encoder-decoder structure for vanishing region (VR, a fixed region centered on VP) segmentation. The third sub-task network shares the encoder-decoder structure with the VR segmentation task and is used for rail segmentation. The VR segmentation task is activated only at the training stage, serving as an auxiliary task to enhance feature learning ability and increase VP detection accuracy. To further improve the accuracies of VP detection and rail segmentation, low-level features is modulated by high-level semantic information before feeding to the decoder stage. With the help of shared feature extraction and auxiliary training, the proposed VP prediction method needs very small training dataset and outperforms other methods in both efficiency and accuracy. INDEX TERMS vanishing point detection, rail segmentation, intrusion detection, multi-task learning, deep learning.

With hydrophobic properties and ordered layered structures, mono-n-dodecyloxy-phosphinyl-cerium (terbium) (MDPCT) organic-inorganic hybrid materials were synthesized using cerium nitrate, terbium nitrate and mono-n-dodecyl phosphate (MDP) surfactant with three functions, hydrophobic group and phosphorus precursor, and characterized by XRD, SEM, TEM, FTIR and PLS. The results show that the solvent affects the interlayer spacing, crystallization and luminescent intensity of the prepared MDPCT materials. MDPCT prepared in water exhibits a more ordered layered structure and a higher degree of crystallinity, as well as stronger luminescent intensity than that prepared in ethanol. Based on the excellent solubility in organic solvents, this MDPCT hybrid luminescent material will be a promising candidate for potential biomedical applications in fluorescent imaging and analysis.

No abstract