基于ToF红外图像的手部轻量化检测算法设计与优化

嵌入式设备上实现快速精准的手部检测主要面临两个挑战：一是复杂的深度学习网络很难实现实时的手部检测；二是场景复杂性导致基于RGB彩色图像的手部检测算法准确率下降。与主流基于RGB图像的检测技术不同，基于ToF红外图像的轻量化手部检测算法实现了红外图像中手部的精准快速检测。首先，通过自主研发设备采集了22 419张静态红外图片，构建了用于手部检测的红外数据集；其次，通过对通用目标检测算法进行轻量化改进，设计了RetinaHand轻量化手部检测网络，其中采用了MobileNetV1和ShuffleNetV2两种不同的轻量化网络作为模型骨干网络，并提出了一种融合注意力机制的特征金字塔结构Attention-FPN；最后，在红外数据集上与常规方法进行了对比实验，验证了该方法的有效性。

Design and optimization of hand lightweight detection algorithm based on ToF infrared images

Implementing fast and accurate hand detection on embedded devices mainly face two challenges: firstly, it is difficult for complex deep learning networks to achieve real-time hand detection. Secondly, the complexity of the scene leads to a decrease in the accuracy of hand detection algorithms based on RGB color images. Unlike mainstream RGB image based detection technologies, this paper adopted a lightweight hand detection algorithm based on ToF infrared images to attain precise and swift hand detection within the infrared images. Firstly, this paper gathered 22 419 static infrared images using this selfengineered equipment, thereby establishing an infrared dataset tailored for hand detection. Subsequently, this paper enhanced a general object detection algorithm to create a lightweight hand detection network known as RetinaHand, using two different lightweight networks, MobileNetV1 and ShuffleNetV2, as the backbone network of the model. Furthermore, this paper proposed an attention-enhanced feature pyramid structure called Attention-FPN. This structure integrated attention mechanisms to enhance the detection process. Ultimately, this paper conducted comparative experiments on the infrared dataset against conventional methods to validate the effectiveness of the method.