Binocular vision calibration is of great importance in 3D machine vision measurement. With respect to binocular vision calibration, the nonlinear optimization technique is a crucial step to improve the accuracy. The existing optimization methods mostly aim at minimizing the sum of reprojection errors for two cameras based on respective 2D image pixels coordinate. However, the subsequent measurement process is conducted in 3D coordinate system which is not consistent with the optimization coordinate system. Moreover, the error criterion with respect to optimization and measurement is different. The equal pixel distance error in 2D image plane leads to diverse 3D metric distance error at different position before the camera. To address these issues, we propose a precise calibration method for binocular vision system which is devoted to minimizing the metric distance error between the reconstructed point through optimal triangulation and the ground truth in 3D measurement coordinate system. In addition, the inherent epipolar constraint and constant distance constraint are combined to enhance the optimization process. To evaluate the performance of the proposed method, both simulative and real experiments have been carried out and the results show that the proposed method is reliable and efficient to improve measurement accuracy compared with conventional method.

With the high growth rates of railway transportation, it is extremely important to detect railway obstacles ahead of the train to ensure safety. Manual and traditional feature-extraction methods have been utilized in this scenario. There are also deep learning-based railway object detection approaches. However, in the case of a complex railway scene, these object detection approaches are either inefficient or have insufficient accuracy, particularly for small objects. To address this issue, we propose a feature-enhanced single-shot detector (FE-SSD). The proposed method inherits a prior detection module of RON and a feature transfer block of FB-Net. It also employs a novel receptive field-enhancement module. Through the integration of these three modules, the feature discrimination and robustness are significantly enhanced. Experimental results for a railway traffic dataset built by our team indicated that the proposed approach is superior to other SSD-derived models, particularly for small-object detection, while achieving real-time performance close to that of the SSD. The proposed method achieved a mean average precision of 0.895 and a frame rate of 38 frames per second on a railway traffic dataset with an input size of $320\times320$ pixels. The experimental results indicate that the proposed method can be used for real-world railway object detection.

With the rapid increase of video surveillance points in the market in recent years, video anomaly detection has gained extensive attention in the security field. At present, the distribution of normal and anomalous data is unbalanced in unlabeled video data. Variational autoencoder (VAE), as one of the typical deep generative models, gets increasingly popular in unsupervised anomaly detection. However, this model is not good at processing time-series data, especially video data. In addition, the strong generalization ability which is over-reconstructing anomaly behavior of many autoencoder-based works leads to the missed anomaly detection. To solve these problems, in this paper, we present a double-flow convolutional long short-term memory variational autoencoder (DF-ConvLSTM-VAE) to model the probabilistic distribution of the normal video in an unsupervised learning scheme, and to reconstruct videos without anomaly objects for anomaly video detection. Experiments verify the effectiveness and competitiveness of our DF-ConvLSTM-VAE on multiple public benchmark datasets. In particular, our model achieves the state-of-the-art performance on anomalous event count.