Occupying the most significant portion of global data traffic, video is being generated in almost every aspect of our life. Because of its huge volume, we are depending much more heavily on machine intelligence based analysis. In the meantime, video coding technology has been continuously improved for better compression efficiency. However, the state-of-the-art video coding standards, such as H.265/HEVC and versatile video coding (VVC), are still designed assuming that the compressed video will be watched by a human later. Such a design is not optimal when the compressed video will be used by computer vision applications. While the human visual system (HVS) is consistently sensitive to the content with high contrast, the impact of pixels on computer vision algorithms is task driven. For example, because of the different categories of objects used to train detection algorithms, the influence of the same image content on those detectors also varies. Therefore, human oriented video coding strategies may not be optimal when the compressed signal is further processed by algorithms, as the encoder is unaware of the task specific information. In this article, taking object detection as an example, we propose a novel video coding strategy for computer vision. By protecting the information according to its importance for an object detector rather than for the human visual system, our proposed method has the potential to achieve a better object detection performance with the same bandwidth. The main contributions of our paper are: 1) the modeling of the relationship between object detection accuracy and bit rate; 2) a back propagation based method to analyze the influence of each pixel on the detection of target objects; 3) an object detection oriented bit allocation and codec control parameter determination scheme; 4) an evaluation metric to compare the impact of video coding strategies on a given object detector over a predefined range of bit rate. Experimental results demonstrate that our proposed algorithm can better preserve the video content vital for object detection than state-of-the-art video coding schemes.
Three-dimensional (3D) object detection is of great significance for avoiding collisions between vehicles and obstacles in autonomous driving. In particular, the recent 3D object detection methods based on supervised learning are widely studied to achieve excellent performance. However, the 3D labels for training in such methods are expensive and often difficult to be collected. To solve this issue, we propose a monocular 3D vehicle detection method. First, we propose a general mathematical K-means-like method for clustering arbitrary object contours into linear equations. Second, the position, orientation and dimensions of the vehicle can be estimated by applying K-means-like method without the need for 3D labels in the contour of the vehicle. Finally, given the 2D object detection, we maximize a posterior probability of vehicle position, orientation and dimensions to improve the accuracy of the 3D object detection based on the results of K-means-like method. We evaluate the proposed algorithm on the dataset collected by the vehicle-side and road-side cameras in the cooperative vehicle infrastructure system (CVIS). Compared with the state-of-art Deep3DBox and SMOKE methods, the evaluated results show that the detection accuracy of 3D object of our method is 1.4% higher than that of Deep3DBox in the vehicle-side system, while for the road-side camera, the proposed method has 3.86% and 4.37% higher accuracy than Deep3DBox and SMOKE, respectively. Thus, the proposed method can be seen as an effective 3D object detection method in the intelligent transportation system and CVIS.
Detecting all kinds of intrusions efficiently is significant to network security. Radial basis function (RBF) neural network is a kind of feed forward neural network, which is widely employed as a real-time pattern classification. In RBF neural network, the center of radial basis function, the variance of radial basis of function and the weight have to be chosen. If they are not appropriately chosen, the RBF neural network may degrade validity and accuracy of modeling. Particle swarm optimization algorithm (PSO) is a member of the wide category of swarm intelligence methods to solve non-linear programming problems. PSO has proved to be competitive with genetic algorithm (GA) in parameter optimization. So PSO is used to optimize the RBF neural network parameters in this work. Therefore, the novel combination method based on RBF neural network and PSO (PSO-RBFNN) is adapted to network intrusion detection. The experimental results show that the proposed model is superior to the conventional RBF neural network.
The quality of infrared images is affected by various degradation factors, such as image blurring and noise pollution. Anisotropic total variation (ATV) has been shown to be a good regularization approach for image deblurring. However, there are two main drawbacks in ATV. First, the conventional ATV regularization just considers the sparsity of the first-order image gradients, thus leading to staircase artifacts. Second, it employs the L1-norm to describe the sparsity of image gradients, while the L1-norm has a limited capacity of depicting the sparsity of sparse variables. To address these limitations of ATV, a high-order total variation is introduced in the ATV deblurring model and the Lp-pseudonorm is adopted to depict the sparsity of low- and high-order total variation. In this way, the recovered image can fit the image priors with clear edges and eliminate the staircase artifacts of the ATV model. The alternating direction method of multipliers is used to solve the proposed model. The experimental results demonstrate that the proposed method does not only remove blurs effectively but is also highly competitive against the state-of-the-art methods, both qualitatively and quantitatively.
21 January 2019 in IEEE Transactions on Circuits and Systems for Video Technology
The newest generation of video coding standard, high efficiency video coding (HEVC), significantly improves the video compression efficiency by introducing more flexible block partitioning structures and richer coding modes than those of previous coding standards; however, the encoders suffer from high computational complexity, which greatly hinders their extensive application. Extensive studies on optimizing the complexity of HEVC encoders have been conducted. However, most studies do not effectively achieve a trade-off between the rate-distortion (RD) performance loss and complexity during rate-distortion optimization (RDO). In this paper, we mathematically define the complexity-constrained RDO problem as a constrained optimization problem of subset selection. Next, based on the classification methodology, the derivation process for this optimization problem is simplified to finding the adaptive threshold function in the feature space with extremely low complexity. The proposed method is also highly general and is applicable to algorithm design for various coding mode decisions, such as coding unit (CU) splitting, prediction unit (PU) partitioning and transform unit (TU) tree decision, and the global optimum can be achieved. Compared with existing methods, the experimental results show that the proposed method can reduce the coding time by 2-16% with the same RD performance loss and can decrease the BD rate by 0.1-1.2% under the same complexity. In addition, this method is capable of flexibly adjusting the complexity under different RDC trade-off requirements.