论文标题
FRDET：基于嵌入式自动驾驶的嵌入式处理器的平衡且轻巧的对象检测器
FRDet: Balanced and Lightweight Object Detector based on Fire-Residual Modules for Embedded Processor of Autonomous Driving
论文作者
论文摘要
对于用于自主驾驶的嵌入式处理器上的部署，对象检测网络应满足所有准确性，实时推理和光模型尺寸要求。常规的深CNN基于CNN的探测器的目的是高精度，使其模型尺寸重量为具有有限的内存空间的嵌入式系统。相比之下，轻质对象探测器受到极大压缩，但精确牺牲了。因此，我们提出了FRDET，这是一种平衡的轻质单阶段对象检测器，以满足嵌入式GPU处理器上用于自动驾驶应用程序的准确性，模型大小和实时处理的所有约束。我们的网络旨在最大程度地提高模型的压缩，同时达到或超过Yolov3的准确性水平。本文提出了燃烧（FR）模块，以设计一个轻巧的网络，该网络通过调整剩余跳过连接来调整火力模块，以较低的精度损失。此外，还应用了边界框的高斯不确定性建模，以进一步提高定位精度。与Yolov3相比，KITTI数据集上的实验表明，FRDET将记忆尺寸降低了50.8％，但将其准确度降低了1.12％。此外，实时检测速度在嵌入式GPU板（NVIDIA Xavier）上达到31.3 fps。与其他Deep CNN对象探测器相比，所提出的网络具有更高的压缩，同时表现出比轻质检测器基准相比的精度。因此，所提出的FRDET是一种用于自主驾驶中实际应用的良好平衡，有效的对象检测器，可以满足准确性，实时推理和光模型大小的所有标准。
For deployment on an embedded processor for autonomous driving, the object detection network should satisfy all of the accuracy, real-time inference, and light model size requirements. Conventional deep CNN-based detectors aim for high accuracy, making their model size heavy for an embedded system with limited memory space. In contrast, lightweight object detectors are greatly compressed but at a significant sacrifice of accuracy. Therefore, we propose FRDet, a lightweight one-stage object detector that is balanced to satisfy all the constraints of accuracy, model size, and real-time processing on an embedded GPU processor for autonomous driving applications. Our network aims to maximize the compression of the model while achieving or surpassing YOLOv3 level of accuracy. This paper proposes the Fire-Residual (FR) module to design a lightweight network with low accuracy loss by adapting fire modules with residual skip connections. In addition, the Gaussian uncertainty modeling of the bounding box is applied to further enhance the localization accuracy. Experiments on the KITTI dataset showed that FRDet reduced the memory size by 50.8% but achieved higher accuracy by 1.12% mAP compared to YOLOv3. Moreover, the real-time detection speed reached 31.3 FPS on an embedded GPU board(NVIDIA Xavier). The proposed network achieved higher compression with comparable accuracy compared to other deep CNN object detectors while showing improved accuracy than the lightweight detector baselines. Therefore, the proposed FRDet is a well-balanced and efficient object detector for practical application in autonomous driving that can satisfies all the criteria of accuracy, real-time inference, and light model size.
