基于深度卷积神经网络的小目标检测算法

A small object detection algorithm based on deep convolutional neural network

针对YOLO目标检测算法在小目标检测方面存在的不足,以及难以在嵌入式平台上达到实时性的问题,设计出了一种基于YOLO算法改进的dense_YOLO目标检测算法。该算法共分为2个阶段:特征提取阶段和目标检测回归阶段。在特征提取阶段,借鉴DenseNet结构的思想,设计了新的基于深度可分离卷积的slim-densenet特征提取模块,增强了小目标的特征传递,减少了参数量,加快了网络的传播速度。在目标检测阶段,提出自适应多尺度融合检测的思想,将提取到的特征进行融合,在不同的特征尺度上进行目标的分类和回归,提高了对小目标的检测准确率。实验结果表明:在嵌入式平台上,针对小目标,本文提出的dense_YOLO目标检测算法相较原YOLO算法mAP指标提高了7%,单幅图像检测时间缩短了15 ms,网络模型大小减少了90 MB,明显优于原算法。

In view of the shortcomings of YOLO object detection algorithm in small object detection, and the difficulty of achieving real-time performance on embedded platforms, this paper designs an improved YOLO object detection algorithm, called dense_YOLO. The algorithm contains two phases: feature extraction phase and object detection regression phase. In the feature extraction phase, based on the idea of DenseNet structure, a new slim-densenet feature extraction module based on deep separable convolution is designed, which enhances the transmission of small object features and reduces the parameter quantity to accelerate the network propagation speed. In the object detection stage, the idea of adaptive multi-scale fusion detection is proposed to fuse the extracted features, and the objects are classified and regressed on different feature scales, which improves the detection accuracy of small objects. Experimental results show that, compared with the original YOLO object detection algorithm, the dense_YOLO object detection algorithm improves mAP by 7%, decreases the single picture detection time by 15 ms, and reduces the model size by 90 MB.