基于改进Efficientdet的自动驾驶场景目标检测

doi:10.3778/j.issn.1002-8331.2109-0190

摘要/Abstract

摘要： 针对自动驾驶场景中车载平台计算资源有限及小目标检测精度较低等问题，提出一种基于Efficientdet的单阶段目标检测框架Efficientdet-Gs。通过重构倒转残差瓶颈MBConv来改进主干网络Efficientnet，在不牺牲精度的同时降低了网络的参数量和计算量；设计多尺度注意力机制模块应用于特征融合网络，进一步提高了对小目标的检测精度；引入Balanced L1 Loss替换原回归损失函数Smooth L1 Loss，解决了损失函数中的平衡性问题。实验结果表明，Efficientdet-Gs的平均计算量相较于Efficientdet下降了25%，在BDD100K测试集上平均检测精度提高了4.8%，平均推理速度提高了5.7%。该框架在车载硬件设备要求较低的情况下能够实现良好的检测效果。

关键词: 自动驾驶, 目标检测, 深度学习, Efficientdet, Ghostnet, 注意力机制

Abstract: Aiming at the problems of limited computing resources on the vehicle-mounted platform and low detection accuracy of small targets in autonomous driving scenarios, a single-stage object detection framework Efficientdet-Gs based on Efficientdet is proposed. The backbone network Efficientnet is improved by reconstructing the inverted residual bottleneck MBConv, which reduces the amount of network parameters and calculations without sacrificing accuracy. The multi-scale attention mechanism module is designed to be applied to the feature fusion network, which further improves the detection accuracy of small targets. The Balanced L1 Loss is introduced to replace the original regression loss function Smooth L1 Loss, which solves the problem of balance in the loss function. Experimental results show that, compared with Efficientdet, the calculation of Efficientdet-Gs is reduced by an average of 25%, the average detection accuracy on the BDD100K test set is increased by 4.8%, and the average inference speed is increased by 5.7%. This framework can achieve good detection results when the hardware requirements of vehicle-mounted equipment are low.

Key words: autonomous driving, object detection, deep learning, Efficientdet, Ghostnet, attention mechanism

李彦辰, 张小俊, 张明路, 沈亮屹. 基于改进Efficientdet的自动驾驶场景目标检测[J]. 计算机工程与应用, 2022, 58(6): 183-191.

LI Yanchen, ZHANG Xiaojun, ZHANG Minglu, SHEN Liangyi. Object Detection in Autonomous Driving Scene Based on Improved Efficientdet[J]. Computer Engineering and Applications, 2022, 58(6): 183-191.

参考文献

[1] HE K，ZHANG X，REN S，at el.Deep residual learning for image recognition[J].IEEE Conference on Computer Vision and Pattern Recognition，2016：770-778.
[2] 郑少武，李巍华，胡坚耀.基于激光点云与图像信息融合的交通环境车辆检测[J].仪器仪表学报，2019，40（12）：143-151.
ZHENG S W，LI W H，HU J Y.Vehicle detection in the traffic environment based on the fusion of laser point cloud and image information[J].Chinese Journal of Scientific Instrument，2019，40（12）：143-151.
[3] WANG H，YU Y，CAI Y，et al.A comparative study of state-of-the-art deep learning algorithms for vehicle detection[J].IEEE Intelligent Transportation Systems Magazine，2019，11（2）：83-95.
[4] GIRSHICK R，DONAHUE J，DARRELL T.Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition，2014：580-587.
[5] GIRSHICK R.Fast R-CNN[C]//IEEE International Conference on Computer Vision，2015：1440-1448.
[6] REN S，HE K，GIRSHICK R，et al.Faster R-CNN：towards real time object detection with region proposal networks[C]//Advances in Neural Information Processing Systems，2015：91-99.
[7] REDMON J，DIVVAL S，GIRSHICK R，et al.You only look once：unifified，real-time object detection[C]//IEEE Conference on Computer Vision and Pattern Recognition，2016：779-788.
[8] LIU W，ANGUELOV D，ERHAN D，et al.SSD：single shot multibox detector[C]//European Conference on Computer Vision.Cham：Springer，2016：21-37.
[9] REDMON J，FARHADI A.YOLOv3：an incremental improvement[J].arXiv：1804.02767，2018.
[10] ZHOU X，WANG D，KR?HENBüHL P.Objects as points[J].arXiv：1904.07850，2019.
[11] LIN T Y，GOYAL P，GIRSHICK R，et al.Focal loss for dense object detection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2020，42（2）：318-327.
[12] 刘晓，崔光照，李正周，等.基于视觉系统分层的小目标运动检测[J].光学精密工程，2019，27（10）：2251-2262.
LIU X，CUI G Z，LI Z Z，et al.Small target motion detection based on layering of vision system[J].Optics and Precision Engineering，2019，27（10）：2251-2262.
[13] TAN M，PANG R，LE Q V.EfficientDet：scalable and efficient object detection[C]//IEEE Conference on Computer Vision and Pattern Recognition，2020：10778-10787.
[14] HAN K，WANG Y，TIAN Q，et al.GhostNet：more features from cheap operations[C]//IEEE/CVF Conference on Computer Vision and Pattern Recognition，2020：1577-1586.
[15] TAN M，LE Q V.Efficientnet：rethinking model scaling for convolutional neural networks[C]//Proceedings of the 36th International Conference on Machine Learning，2019：6105-6114.
[16] PANG J，CHEN K，SHI J，et al.Libra R-CNN：towards balanced learning for object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2019：821-830.
[17] HU J，SHEN L，SUN G，et al.Squeeze-and-excitation networks[C]//IEEE Conference on Computer Vision and Pattern Recognition，2018：7131-7141.
[18] WANG Q，WU B，ZHU P，et al.ECA-Net：efficient channel attention for deep convolutional neural networks[C]//IEEE Conference on Computer Vision and Pattern Recognition，2020：11531-11539.
[19] ZHANG X，ZHOU X，LIN M，et al.ShuffleNet：an extremely efficient convolutional neural network for mobile devices[C]//IEEE Conference on Computer Vision and Pattern Recognition，2018：6848-6856.
[20] MARK S，ANDREW H，MENGLONG Z，et al.Mobilenetv2：inverted residuals and linear bottlenecks[C]//IEEE Conference on Computer Vision and Pattern Recognition，2018：4510-4520.
[21] HOWARD A，SANDLER M，CHEN B，et al.Searching for Mobilenetv3[C]//Proceedings of IEEE/CVF International Conference on Computer Vision，2019：1314-1324.
[22] SHELHAMER E，LONG J，DARREL T.Fully convolutional networks for semantic segmentation[C]//IEEE Conference on Computer Vision and Pattern Recognition，2015：640-651.
[23] LIU S，QI L，QIN H，et al.Path aggregation network for instance segmentation[C]//IEEE Conference on Computer Vision and Pattern Recognition，2017：8759-8768.
[24] HYUHJAE L，HYO-EUN K，HYEONSEOB N.SRM：a style-based recalibration module for convolutional neural networks[J].arXiv：1903.10829，2019.
[25] CAI Z，VASCONCELOS N.Cascade R-CNN：delving into high quality object detection[C]//IEEE Conference on Computer Vision and Pattern Recognition，2018：6154-6162.