College of Engineering, Kettering University, Flint, MI 48504, USA.
Sensors (Basel). 2023 Apr 14;23(8):3992. doi: 10.3390/s23083992.
For many automotive functionalities in Advanced Driver Assist Systems (ADAS) and Autonomous Driving (AD), target objects are detected using state-of-the-art Deep Neural Network (DNN) technologies. However, the main challenge of recent DNN-based object detection is that it requires high computational costs. This requirement makes it challenging to deploy the DNN-based system on a vehicle for real-time inferencing. The low response time and high accuracy of automotive applications are critical factors when the system is deployed in real time. In this paper, the authors focus on deploying the computer-vision-based object detection system on the real-time service for automotive applications. First, five different vehicle detection systems are developed using transfer learning technology, which utilizes the pre-trained DNN model. The best performing DNN model showed improvements of 7.1% in Precision, 10.8% in Recall, and 8.93% in F1 score compared to the original YOLOv3 model. The developed DNN model was optimized by fusing layers horizontally and vertically to deploy it in the in-vehicle computing device. Finally, the optimized DNN model is deployed on the embedded in-vehicle computing device to run the program in real-time. Through optimization, the optimized DNN model can run 35.082 fps (frames per second) on the NVIDIA Jetson AGA, 19.385 times faster than the unoptimized DNN model. The experimental results demonstrate that the optimized transferred DNN model achieved higher accuracy and faster processing time for vehicle detection, which is vital for deploying the ADAS system.
对于高级驾驶辅助系统 (ADAS) 和自动驾驶 (AD) 中的许多汽车功能，使用最先进的深度神经网络 (DNN) 技术来检测目标对象。然而，基于最新 DNN 的对象检测的主要挑战在于它需要高计算成本。这一要求使得在车辆上部署基于 DNN 的系统进行实时推断具有挑战性。在实时部署系统时，汽车应用的低响应时间和高精度是关键因素。在本文中，作者专注于将基于计算机视觉的对象检测系统部署到汽车应用的实时服务中。首先，使用迁移学习技术开发了五个不同的车辆检测系统，该技术利用了预先训练好的 DNN 模型。表现最好的 DNN 模型在精度上提高了 7.1%，在召回率上提高了 10.8%，在 F1 得分上提高了 8.93%，与原始的 YOLOv3 模型相比。通过水平和垂直融合层对开发的 DNN 模型进行了优化，以将其部署到车载计算设备中。最后，将优化后的 DNN 模型部署到嵌入式车载计算设备上，以便实时运行程序。通过优化，优化后的 DNN 模型在 NVIDIA Jetson AGA 上可以达到 35.082 fps（每秒帧数），比未经优化的 DNN 模型快 19.385 倍。实验结果表明，优化后的迁移 DNN 模型在车辆检测方面实现了更高的准确性和更快的处理时间，这对于部署 ADAS 系统至关重要。
