It is necessary to improve the performance of the object detection algorithm in resource-constrained embedded devices by lightweight improvement. In order to further improve the recognition accuracy of the algorithm for small target objects, this paper integrates 5 × 5 deep detachable convolution kernel on the basis of MobileNetV2-SSDLite model, extracts features of two special convolutional layers in addition to detecting the target, and designs a new lightweight object detection network—Lightweight Microscopic Detection Network (LMS-DN). The network can be implemented on embedded devices such as NVIDIA Jetson TX2. The experimental results show that LMS-DN only needs fewer parameters and calculation costs to obtain higher identification accuracy and stronger anti-interference than other popular object detection models.

中文翻译：

---

用于嵌入式设备上驾驶员手持呼叫实时检测的轻量级对象检测网络

有必要通过轻量级改进来提高资源受限嵌入式设备中对象检测算法的性能。为了进一步提高算法对小目标物体的识别精度，本文在MobileNetV2-SSDLite模型的基础上，集成了5×5深度可拆卸卷积核，提取了两个特殊的卷积层特征，并进行了目标检测。设计了一种新的轻型物体检测网络-轻型微观检测网络（LMS-DN）。该网络可以在诸如NVIDIA Jetson TX2之类的嵌入式设备上实现。实验结果表明，与其他流行的物体检测模型相比，LMS-DN只需要较少的参数和计算成本即可获得更高的识别精度和更强的抗干扰能力。