当前位置: X-MOL 学术J. Real-Time Image Proc. › 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.)
M-YOLO: an object detector based on global context information for infrared images
Journal of Real-Time Image Processing ( IF 2.9 ) Pub Date : 2022-08-12 , DOI: 10.1007/s11554-022-01242-y
Zhiqiang Hou , Ying Sun , Hao Guo , Juanjuan Li , Sugang Ma , Jiulun Fan

Object detection is an important task in computer vision. While visible (VS) images are adequate for detecting objects in most scenarios, infrared (IR) images can extend the capabilities of object detection to night-time or occluded objects. For IR images, we proposes an infrared object detector based on global context information. Combined with the lightweight network (MobileNetV2) to extract features, therefore the detector is named M-YOLO. Then, dedicated to enhancing the global information perception capability of the model, this paper proposes a global contextual information aggregation model. To preserve multi-scale information and enhance expressiveness of features, a top-down and bottom-up parallel feature fusion method is proposed. Only two detection heads are used to implement a lightweight model, which improves detection accuracy and speed. We use the self-built IR dataset (GIR) and the public IR dataset (FLIR) to verify the superiority of the model. Compared with YOLOv4 (78.1%), the average accuracy of M-YOLO (83.4%) is improved by 5.3% on the FLIR dataset. The detection time (4.33 ms) is less, with a detection speed of 30.6 FPS. On the GIR dataset, the detection accuracy (76.1%) is 6.4% higher than that of YOLOv4 (69.7%), and the detection time (6.84 ms) is lower. Our method improves the performance of IR object detection. The method is able to detect IR ground targets in complex environments, and the detection speed meets the real-time requirements.



中文翻译:

M-YOLO:基于全局上下文信息的红外图像目标检测器

目标检测是计算机视觉中的一项重要任务。虽然可见 (VS) 图像足以在大多数情况下检测物体,但红外 (IR) 图像可以将物体检测的能力扩展到夜间或被遮挡的物体。对于红外图像,我们提出了一种基于全局上下文信息的红外目标检测器。结合轻量级网络(MobileNetV2)提取特征,因此检测器命名为 M-YOLO。然后,为了增强模型的全局信息感知能力,本文提出了一种全局上下文信息聚合模型。为了保留多尺度信息并增强特征的表达能力,提出了一种自顶向下和自底向上的并行特征融合方法。仅使用两个检测头来实现轻量级模型,从而提高检测精度和速度。我们使用自建红外数据集(GIR)和公共红外数据集(FLIR)来验证模型的优越性。与 YOLOv4 (78.1%) 相比,M-YOLO (83.4%) 在 FLIR 数据集上的平均准确率提高了 5.3%。检测时间(4.33 ms)更短,检测速度为30.6 FPS。在 GIR 数据集上,检测精度(76.1%)比 YOLOv4(69.7%)高 6.4%,检测时间(6.84 ms)更低。我们的方法提高了红外目标检测的性能。该方法能够对复杂环境下的红外地面目标进行检测,检测速度满足实时性要求。4%)在 FLIR 数据集上提高了 5.3%。检测时间(4.33 ms)更短,检测速度为30.6 FPS。在 GIR 数据集上,检测精度(76.1%)比 YOLOv4(69.7%)高 6.4%,检测时间(6.84 ms)更低。我们的方法提高了红外目标检测的性能。该方法能够对复杂环境下的红外地面目标进行检测,检测速度满足实时性要求。4%)在 FLIR 数据集上提高了 5.3%。检测时间(4.33 ms)更短,检测速度为30.6 FPS。在 GIR 数据集上,检测精度(76.1%)比 YOLOv4(69.7%)高 6.4%,检测时间(6.84 ms)更低。我们的方法提高了红外目标检测的性能。该方法能够对复杂环境下的红外地面目标进行检测,检测速度满足实时性要求。

更新日期:2022-08-13
down
wechat
bug