Urban street scene analysis using lightweight multi-level multi-path feature aggregation network

Urban street scene analysis is an important problem in computer vision with many off-line models achieving outstanding semantic segmentation results. However, it is an ongoing challenge for the research community to develop and optimize the deep neural architecture with real-time low computing requirements whilst maintaining good performance. Balancing between model complexity and performance has been a major hurdle with many models dropping too much accuracy for a slight reduction in model size and unable to handle high-resolution input images. The study aims to address this issue with a novel model, named M2FANet, that provides a much better balance between model’s efficiency and accuracy for scene segmentation than other alternatives. The proposed optimised backbone helps to increase model’s efficiency whereas, suggested Multi-level Multi-path (M2) feature aggregation approach enhances model’s performance in the real-time environment. By exploiting multi-feature scaling technique, M2FANet produces state-of-the-art results in resource-constrained situations by handling full input resolution. On the Cityscapes benchmark data set, the proposed model produces 68.5% and 68.3% class accuracy on validation and test sets respectively, whilst having only 1.3 million parameters. Compared with all real-time models of less than 5 million parameters, the proposed model is the most competitive in both performance and real-time capability.

Inter-Level Feature Balanced Fusion Network for Street Scene Segmentation

Semantic segmentation, as a pixel-level recognition task, has been widely used in a variety of practical scenes. Most of the existing methods try to improve the performance of the network by fusing the information of high and low layers. This kind of simple concatenation or element-wise addition will lead to the problem of unbalanced fusion and low utilization of inter-level features. To solve this problem, we propose the Inter-Level Feature Balanced Fusion Network (IFBFNet) to guide the inter-level feature fusion towards a more balanced and effective direction. Our overall network architecture is based on the encoder–decoder architecture. In the encoder, we use a relatively deep convolution network to extract rich semantic information. In the decoder, skip-connections are added to connect and fuse low-level spatial features to restore a clearer boundary expression gradually. We add an inter-level feature balanced fusion module to each skip connection. Additionally, to better capture the boundary information, we added a shallower spatial information stream to supplement more spatial information details. Experiments have proved the effectiveness of our module. Our IFBFNet achieved a competitive performance on the Cityscapes dataset with only finely annotated data used for training and has been greatly improved on the baseline network.

Denoising of Tourist Street Scene Image Based on ROF Model of Second-Order Partial Differential Equation

The noise pollution in tourist street view images is caused by various reasons. A major challenge that researchers have been facing is to find a way to effectively remove noise. Although in the past few decades people have proposed many methods of denoising tourist street scene images, the research on denoising technology of tourist street scene images is still not outdated. There is no doubt that it has become a basic and important research topic in the field of digital image processing. The evolutionary diffusion method based on partial differential equations is helpful to improve the quality of noisy tourist street scene images. This method can process tourist street scene images according to people’s expected diffusion behavior. The adaptive total variation model proposed in this paper is improved on the basis of the total variation model and the Gaussian thermal diffusion model. We analyze the classic variational PDE-based denoising model and get a unified variational PDE energy functional model. We also give a detailed analysis of the diffusion performance of the total variational model and then propose an adaptive total variational diffusion model. By improving the diffusion coefficient and introducing a curvature operator that can distinguish details such as edges, it can effectively denoise the tourist street scene image, and it also has a good effect on avoiding the step effect. Through the improvement of the ROF model, the loyalty term and regular term of the model are parameterized, the adaptive total variation denoising model of this paper is established, and a detailed analysis is carried out. The experimental results show that compared with some traditional denoising models, the model in this paper can effectively suppress the step effect in the denoising process, while protecting the texture details of the edge area of the tourist street scene image. In addition, the model in this paper is superior to traditional denoising models in terms of denoising performance and texture structure protection.

EAR-Net: Efficient Atrous Residual Network for Semantic Segmentation of Street Scenes Based on Deep Learning

Segmentation of street scenes is a key technology in the field of autonomous vehicles. However, conventional segmentation methods achieve low accuracy because of the complexity of street landscapes. Therefore, we propose an efficient atrous residual network (EAR-Net) to improve accuracy while maintaining computation costs. First, we performed feature extraction and restoration, utilizing depthwise separable convolution (DSConv) and interpolation. Compared with conventional methods, DSConv and interpolation significantly reduce computation costs while minimizing performance degradation. Second, we utilized residual learning and atrous spatial pyramid pooling (ASPP) to achieve high accuracy. Residual learning increases the ability to extract context information by preventing the problem of feature and gradient losses. In addition, ASPP extracts additional context information while maintaining the resolution of the feature map. Finally, to alleviate the class imbalance between the image background and objects and to improve learning efficiency, we utilized focal loss. We evaluated EAR-Net on the Cityscapes dataset, which is commonly used for street scene segmentation studies. Experimental results showed that the EAR-Net had better segmentation results and similar computation costs as the conventional methods. We also conducted an ablation study to analyze the contributions of the ASPP and DSConv in the EAR-Net.

Imperceptible Adversarial Attacks against Traffic Scene Recognition

Adversarial examples have begun to receive widespread attention owning to their potential destructions to the most popular DNNs. They are crafted from original images by embedding well calculated perturbations. In some cases the perturbations are so slight that neither human eyes nor monitoring systems can notice easily and such imperceptibility makes them have greater concealment and damage. For the sake of investigating the invisible dangers in the applications of traffic DNNs, we focus on imperceptible adversarial attacks on different traffic vision tasks, including traffic sign classification, lane detection and street scene recognition. We propose an universal logits map-based attack architecture against image semantic segmentation, and design two targeted attack approaches on it. All the attack algorithms generate the micro-noise adversarial examples by the iterative method of gradient descent optimization. All of them can achieve 100% attack rate but with very low distortion, among which, the mean MAE (Mean Absolute Error) of perturbation noise based on traffic sign classifier attack is as low as 0.562, and the other two algorithms based on semantic segmentation are only 1.574 and 1.503. We believe that our research on imperceptible adversarial attacks can be of substantial reference to the security of DNNs applications.

Israel in Egypt

Weill’s evolving relationship with his Jewish heritage is apparent in several of his works. Although the pageant The Eternal Road (1937) premiered in the United States, it was conceived with European audiences in mind. Thus, Weill’s score draws on both German and Jewish musical styles and forms in order to prove that—despite Nazi declarations—the two identities were not in conflict. He wrote his first Jewish characters for the mainstream Broadway stage in Street Scene (1947), which explores the place of Jews within a multicultural community. Lost in the Stars (1949) represents the culmination of Weill’s lifelong passion for racial equality, and hearkens back to some aspects of The Eternal Road, aligning it with emergent conceptions and agendas a “Judeo-Christian” community.