Explore the vast range of titles available.

Intelligent vehicles should not only be able to detect various obstacles, but also identify their categories so as to take an appropriate protection and intervention. However, the scenarios of object detection are usually complex and changeable, so how to balance the relationship between accuracy and speed is a difficult task of object detection. This paper proposes a multi-object detection algorithm using DarkNet-53 and dense convolution network (DenseNet) to further ensure maximum information flow between layers. Three 8-layer dense blocks are used to replace the last three downsampling layers in DarkNet-53 structure, so that the network can make full use of multi-layer convolution features before prediction. The loss function of coordinate prediction error in YOLOv3 is further improved to improve the detection accuracy. Extensive experiments are conducted on the public KITTI and Pascal VOC datasets, and the results demonstrate that the proposed algorithm has better robustness, and the network model is more suitable for the traffic scene in the real driving environment and has better adaptability to the objects with long distance, small size and partial occlusion.

This paper proposes a novel unsupervised learning framework for depth recovery and camera ego-motion estimation from monocular video. The framework exploits the optical flow (OF) property to jointly train the depth and the ego-motion models. Unlike the existing unsupervised methods, our method extracts the features from the optical flow rather than from the raw RGB images, thereby enhancing unsupervised learning. In addition, we exploit the forward-backward consistency check of the optical flow to generate a mask of the invalid region in the image, and accordingly, eliminate the outlier regions such as occlusion regions and moving objects for the learning. Furthermore, in addition to using view synthesis as a supervised signal, we impose additional loss functions, including optical flow consistency loss and depth consistency loss, as additional supervision signals on the valid image region to further enhance the training of the models. Substantial experiments on multiple benchmark datasets demonstrate that our method outperforms other unsupervised methods.

Visual odometry estimates the ego-motion of an agent (e.g., vehicle and robot) using image information and is a key component for autonomous vehicles and robotics. This paper proposes a robust and precise method for estimating the 6-DoF ego-motion, using a stereo rig with optical flow analysis. An objective function fitted with a set of feature points is created by establishing the mathematical relationship between optical flow, depth and camera ego-motion parameters through the camera’s 3-dimensional motion and planar imaging model. Accordingly, the six motion parameters are computed by minimizing the objective function, using the iterative Levenberg–Marquard method. One of key points for visual odometry is that the feature points selected for the computation should contain inliers as much as possible. In this work, the feature points and their optical flows are initially detected by using the Kanade–Lucas–Tomasi (KLT) algorithm. A circle matching is followed to remove the outliers caused by the mismatching of the KLT algorithm. A space position constraint is imposed to filter out the moving points from the point set detected by the KLT algorithm. The Random Sample Consensus (RANSAC) algorithm is employed to further refine the feature point set, i.e., to eliminate the effects of outliers. The remaining points are tracked to estimate the ego-motion parameters in the subsequent frames. The approach presented here is tested on real traffic videos and the results prove the robustness and precision of the method.

Obstacle detection is the basis for the Advanced Driving Assistance System (ADAS) to take obstacle avoidance measures. However, it is a very essential and challenging task to detect unexpected obstacles on the road. To this end, an unexpected obstacle detection method based on computer vision is proposed. We first present two independent methods for the detection of unexpected obstacles: a semantic segmentation method that can highlight the contextual information of unexpected obstacles on the road and an open-set recognition algorithm that can distinguish known and unknown classes according to the uncertainty degree. Then, the detection results of the two methods are input into the Bayesian framework in the form of probabilities for the final decision. Since there is a big difference between semantic and uncertainty information, the fusion results reflect the respective advantages of the two methods. The proposed method is tested on the Lost and Found dataset and evaluated by comparing it with the various obstacle detection methods and fusion strategies. The results show that our method improves the detection rate while maintaining a relatively low false-positive rate. Especially when detecting unexpected long-distance obstacles, the fusion method outperforms the independent methods and keeps a high detection rate.

Obstacle detection is the primary task of the Advanced Driving Assistance System (ADAS). However, it is very difficult to achieve accurate obstacle detection in complex traffic scenes. To this end, this paper proposes an obstacle detection method based on the local spatial features of point clouds. Firstly, the local spatial point cloud of a superpixel is obtained through stereo matching and the SLIC image segmentation algorithm. Then, the probability of the obstacle in the corresponding area is estimated from the spatial feature information of the local plane normal vector and the superpixel point-cloud height, respectively. Finally, the detection results of the two methods are input into the Bayesian framework in the form of probabilities for the final decision. In order to describe the traffic scene efficiently and accurately, the detection results are further transformed into a multi-layer stixel representation. We carried out experiments on the KITTI dataset and compared several obstacle detection methods. The experimental results indicate that the proposed method has advantages in terms of its Pixel-wise True Positive Rate (PTPR) and Pixel-wise False Positive Rate (PFPR), particularly in complex traffic scenes, such as uneven roads.

Detecting abnormal events in crowded scenes is an important but challenging task in computer vision. Contextual information is useful for discovering salient events in scenes; however, it cannot be characterized well by commonly used pixel-based descriptors, such as the HOG descriptor. In this paper, we propose contextual gradients between two local regions and then construct a histogram of oriented contextual gradient (HOCG) descriptor for abnormal event detection based on the contextual gradients. The HOCG descriptor is a distribution of contextual gradients of sub-regions in different directions, which can effectively characterize the compositional context of events. We conduct extensive experiments on several public datasets and compare the experimental results using state-of-the-art approaches. Qualitative and quantitative analysis of experimental results demonstrate the effectiveness of the proposed HOCG descriptor.

The organic Rankine cycle (ORC) has been widely studied to recover waste heat from internal combustion engines in commercial on-road vehicles. To achieve a cost-effective ORC, a trade-off between factors such as costs, power outputs, back pressure, and weight needs to be carefully worked out. However, the trade-off is still a huge challenge in engine waste heat recovery. In this study, a thermoeconomic optimization study of a vehicle-mounted ORC unit is proposed to recover waste heat from various exhaust gas conditions of a light-duty vehicle. The optimization is carried out for four organic working fluids with different critical temperatures, respectively. Under the investigated working fluids, the lower specific investment cost (SIC) and higher mean net output power (MEOP) of ORC can be achieved using the organic working fluid with higher critical temperature. The maximum mean net output power is obtained by taking RC490 as working fluid and the payback period (PB) is 3.01 years when the petrol is EUR 1.5 per liter. The proposed strategy is compared with a thermodynamic optimization method with MEOP as an optimized objective. It shows that the proposed strategy reached SIC results more economically. The importance of taking the ORC weight and the back pressure caused by ORC installation into consideration during the preliminary design phase is highlighted.

This article is concerned with the robust model predictive control (RMPC) problem for polytopic uncertain systems under the round-robin (RR) scheduling in the high-rate communication channel. From a set of sensors to the controller, several sensors transmit the data to the remote controller via a shared high-rate communication network, data collision might happen if these sensors start transmissions at the same time. For the sake of preventing data collision in the high-rate communication channel, a communication scheduling known as RR is used to arrange the data transmission order, where only one node with token is allowed to send data at each transmission instant. In accordance with the token-dependent Lyapunov-like approach, the aim of the problem addressed is to design a set of controllers in the framework of RMPC such that the asymptotical stability of the closed-loop system is guaranteed. By taking the effect of the underlying RR scheduling in the high-rate communication channel into consideration, sufficient conditions are obtained by solving a terminal constraint set of an auxiliary optimization problem. In addition, an algorithm including both off-line and online parts is provided to find a sub-optimal solution. Finally, two simulation examples are used to demonstrate the usefulness and effectiveness of the proposed RMPC strategy.

This paper analyzes the development trend of global artificial intelligence from the perspective of bibliometrics. From the publishing trend, the number of papers published in the field of artificial intelligence is growing rapidly. China and the United States are among the top countries in the output of scientific research papers, and India has the fastest cumulative growth rate. In the research direction, the research on computer vision, image, deep learning and neural network is the research hotspot in recent years.

In this paper, the bibliography included in Web of Science is taken as the data sample. This paper analyzes articles and reviews published from 2010 to 2020 in the field of computer vision and graphics to reveal the major countries or regions. We use leiden-type community algorithm to identify research topics. Besides, we explore the research fronts in the field of computer vision and graphics based on highly cited papers. The results show that the research on computer vision and graphics in the United States started earlier. The United States has always been in the leading position. China has developed rapidly in recent years. The United Kingdom, South Korea and India are also prominent. Deep learning, face recognition, image retrieval and volume rendering are the hottest research topics in the field of computer vision and graphics. Convolutional neural network and deep learning are the most emerging research fronts in the field of computer vision and graphics.