Real-Time Semantic Understanding and Segmentation of Urban Scenes for Vehicle Visual Sensors by Optimized DCNN Algorithm

Abstract

The modern urban environment is becoming more and more complex. In helping us identify surrounding objects, vehicle vision sensors rely more on the semantic segmentation ability of deep learning networks. The performance of a semantic segmentation network is essential. This factor will directly affect the comprehensive level of driving assistance technology in road environment perception. However, the existing semantic segmentation network has a redundant structure, many parameters, and low operational efficiency. Therefore, to reduce the complexity of the network and reduce the number of parameters to improve the network efficiency, based on the deep learning (DL) theory, a method for efficient image semantic segmentation using Deep Convolutional Neural Network (DCNN) is deeply studied. First, the theoretical basis of the convolutional neural network (CNN) is briefly introduced, and the real-time semantic segmentation technology of urban scenes based on DCNN is recommended in detail. Second, the atrous convolution algorithm and the multi-scale parallel atrous spatial pyramid model are introduced. On the basis of this, an Efficient Symmetric Network (ESNet) of real-time semantic segmentation model for autonomous driving scenarios is proposed. The experimental results show that: (1) On the Cityscapes dataset, the ESNet structure achieves 70.7% segmentation accuracy for the 19 semantic categories set, and 87.4% for the seven large grouping categories. Compared with other algorithms, the accuracy has increased to varying degrees. (2) On the CamVid dataset, compared with segmentation networks of multiple lightweight real-time images, the parameters of the ESNet model are around 1.2 m, the highest FPS value is around 90 Hz, and the highest mIOU value is around 70%. In seven semantic categories, the segmentation accuracy of the ESNet model is the highest at around 98%. From this, we found that the ESNet significantly improves segmentation accuracy while maintaining faster forward inference speed. Overall, the research not only provides technical support for the development of real-time semantic understanding and segmentation of DCNN algorithms but also contributes to the development of artificial intelligence technology.

Development of an Autonomous Driving Vehicle for Garbage Collection in Residential Areas

“…Chen et al [ 12 ] presented a semantic segmentation method in urban scenes using reality-oriented adaptation networks (ROAD-Net) to convert synthetic data acquired in a virtual environment to an actual data domain. Moreover, Li et al [ 14 ] proposed an Efficient Symmetric Network (ESNet) of a real-time semantic segmentation model for autonomous driving. In addition to images, studies on semantic segmentation using LiDAR have also been conducted.…”

“…Recently, with the rapid development of deep learning, the technology for recognizing the surrounding environment through sensor data has also developed significantly. These deep learning technologies are commonly used for recognizing lanes through cameras [ 1 , 2 , 3 , 4 , 5 , 6 , 7 , 8 , 9 , 10 ] or for recognizing surrounding objects [ 11 , 12 , 13 , 14 ], or as a method for simultaneously recognizing surrounding objects using the camera and lidar [ 15 , 16 ] in autonomous vehicles. Along with various high-precision sensors and deep learning technologies described above, research and commercialization of autonomous vehicles that can autonomously drive on roads without human intervention are also rapidly progressing.…”

Adaptive Rectified Linear Unit (Arelu) for Classification Problems to Solve Dying Problem in Deep Learning

“…This approach allows the use of gradient methods, such as gradient descent or stochastic gradient descent, to train multilayer networks and update weights to reduce loss [5] [6]. ReLU as a nonlinear AF has gained a lot of interest in research due to its simplicity, low computation cost and it avoids the vanishing gradient problem that inherent to the earliest AFs like tanh and sigmoid [7]. Despite all the previous advantages of this function, it has a problem called the Dying ReLU problem, which indicates that the neuron becomes inactive and outputs zero only for any input.…”

“…∑ ∑ (7) Backpropagation in a network aims to make a change in the error value with respect to weights and this process is called derivative because its goal is to make a change in one value with respect to another. The first derivative of this function is: The most effected activation function used in the output layer in the case of multi-layer classification problems is Softmax, which converts the raw outputs of a neural network into a vector of probability scores between 0 and 1.…”