当前位置: X-MOL 学术Signal Process. Image Commun. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
FD-SSD: An improved SSD object detection algorithm based on feature fusion and dilated convolution
Signal Processing: Image Communication ( IF 3.4 ) Pub Date : 2021-08-17 , DOI: 10.1016/j.image.2021.116402
Qunjie Yin 1 , Wenzhu Yang 1 , Mengying Ran 1 , Sile Wang 1
Affiliation  

Objects that occupy a small portion of an image or a frame contain fewer pixels and contains less information. This makes small object detection a challenging task in computer vision. In this paper, an improved Single Shot multi-box Detector based on feature fusion and dilated convolution (FD-SSD) is proposed to solve the problem that small objects are difficult to detect. The proposed network uses VGG-16 as the backbone network, which mainly includes a multi-layer feature fusion module and a multi-branch residual dilated convolution module. In the multi-layer feature fusion module, the last two layers of the feature map are up-sampled, and then they are concatenated at the channel level with the shallow feature map to enhance the semantic information of the shallow feature map. In the multi-branch residual dilated convolution module, three dilated convolutions with different dilated ratios based on the residual network are combined to obtain the multi-scale context information of the feature without losing the original resolution of the feature map. In addition, deformable convolution is added to each detection layer to better adapt to the shape of small objects. The proposed FD-SSD achieved 79.1% mAP and 29.7% mAP on PASCAL VOC2007 dataset and MS COCO dataset respectively. Experimental results show that FD-SSD can effectively improve the utilization of multi-scale information of small objects, thus significantly improve the effect of the small object detection.



中文翻译:

FD-SSD:一种基于特征融合和扩张卷积的改进SSD物体检测算法

占据图像或帧一小部分的对象包含较少的像素和较少的信息。这使得小物体检测成为计算机视觉中的一项具有挑战性的任务。本文提出了一种改进的基于特征融合和扩张卷积的Single Shot multi-box Detector(FD-SSD)来解决小物体难以检测的问题。提出的网络使用VGG-16作为骨干网络,主要包括一个多层特征融合模块和一个多分支残差扩张卷积模块。在多层特征融合模块中,对特征图的最后两层进行上采样,然后在通道级别与浅层特征图进行级联,以增强浅层特征图的语义信息。在多分支残差扩张卷积模块中,将基于残差网络的三个不同扩张率的扩张卷积组合起来,在不损失特征图原始分辨率的情况下,获得特征的多尺度上下文信息。此外,每个检测层都加入了可变形卷积,以更好地适应小物体的形状。提出的 FD-SSD 在 PASCAL VOC2007 数据集和 MS COCO 数据集上分别实现了 79.1% mAP 和 29.7% mAP。实验结果表明,FD-SSD可以有效提高小物体多尺度信息的利用率,从而显着提高小物体检测的效果。每个检测层都加入了可变形卷积,以更好地适应小物体的形状。提出的 FD-SSD 在 PASCAL VOC2007 数据集和 MS COCO 数据集上分别实现了 79.1% mAP 和 29.7% mAP。实验结果表明,FD-SSD可以有效提高小物体多尺度信息的利用率,从而显着提高小物体检测的效果。每个检测层都加入了可变形卷积,以更好地适应小物体的形状。提出的 FD-SSD 在 PASCAL VOC2007 数据集和 MS COCO 数据集上分别实现了 79.1% mAP 和 29.7% mAP。实验结果表明,FD-SSD可以有效提高小物体多尺度信息的利用率,从而显着提高小物体检测的效果。

更新日期:2021-08-24
down
wechat
bug