Scene terrain classification for autonomous vehicle navigation based on semantic segmentation method

Abstract

Autonomous transportation is a new paradigm of an Industry 5.0 cyber-physical system that provides a lot of opportunities in smart logistics applications. The safety and reliability of deep learning-driven systems are still a question under research. The safety of an autonomous guided vehicle is dependent on the proper selection of sensors and the transmission of reflex data. Several academics worked on sensor-based difficulties by developing a sensor correction system and fine-tuning algorithms to regulate the system’s efficiency and precision. In this paper, the introduction of vision sensor and its scene terrain classification using a deep learning algorithm is performed with proposed datasets during sensor failure conditions. The proposed classification technique is to identify the mobile robot obstacle and obstacle-free path for smart logistic vehicle application. To analyze the information from the acquired image datasets, the proposed classification algorithm employs segmentation techniques. The analysis of proposed dataset is validated with U-shaped convolutional network (U-Net) architecture and region-based convolutional neural network (Mask R-CNN) architecture model. Based on the results, the selection of 1400 raw image datasets is trained and validated using semantic segmentation classifier models. For various terrain dataset clusters, the Mask R-CNN classifier model method has the highest model accuracy of 93%, that is, 23% higher than the U-Net classifier model algorithm, which has the lowest model accuracy nearly 70%. As a result, the suggested Mask R-CNN technique has a significant potential of being used in autonomous vehicle applications.

A lightweight network with multi-scale information interaction attention for real-time semantic segmentation

“…To obtain richer semantic information, we set three different dilation rates in the MSI block of each stage for comparison, as shown in Table II. We conclude that the network performance improves by 0.4 when the expansion rate is [4,8,16] compared with [2,4,8]. This finding is because a larger dilation rate enables the network to have a broader receptive field and encode more surrounding information.…”

“…It is a basic task in computer vision [1,2,3,4]. With the rapid development of deep learning, semantic segmentation has gradually been applied to the fields of robotics [5], autonomous vehicles [6,7] and biomedical image analysis [8], among others. However, these applications, particularly those dealing with real-time scenarios, have strict accuracy, model size, inference speed and computational cost requirements.…”

An Ultra Fast Semantic Segmentation Model for AMR’s Path Planning

“…The 2D semantic labeling competition is recommended as a solution to this issue in [29]. In [30], Fusic et al presented a DL algorithm for scene terrain categorization based on visual sensors. Even though the process obtains a high processing speed, its precision remains quite low when environmental factors change.…”

“…Shelhamer et al, [31] converted modern classifier networks (AlexNet, VGG, and GoogLeNet) into fully convolutional networks (FCNs) to improve segmentation model performance and accuracy. Wang et al, used VGG-FCN models such as [30] or Unet [32] to address the image segmentation problem yields accurate results, but is unsuitable for infrastructure deployment due to their high computational cost. Rusli et al, [33] navigated mobile robot using the Canny edge algorithm and Hough line transform.…”

Adaptive coordination control strategy for path-following of DDAEV with neural network based moving weight coefficients

“…Recent decades have witnessed an increasing attention on the integration of autonomous vehicles and artificial intelligence technology, toward achieving an intelligent transport system, such as the autonomous ground vehicle (AGV) (Fényes et al, 2021; Xia et al, 2020; Xie et al, 2021b). This is because intelligent transport system could improve vehicle safety and road utilization, and could also alleviate traffic congestion (Du et al, 2020; Fernandez et al, 2020; Julius Fusic et al, 2021). The in-wheel motors of distributed drive vehicles have been proven to be able to produce accurate, flexible and fast torque response for each driven wheel (Jin et al, 2018; Li et al, 2021a; Sato et al, 2015), demonstrating the potentiality of distributed drive vehicle in improving vehicle handling, flexibility and safety (Xin et al, 2017; Zhang et al, 2017).…”