Object detection plays an important role in computer vision. It has a variety of applications, including security detection, vehicle recognition, and service robots. With the continuous improvement of public databases and the development of deep learning, object detection has witnessed significant breakthroughs. However, the object detection of sweeping robots during operations should consider various factors, including the camera angle, indoor scenery, and identification of object category. To the best of our knowledge, no corresponding database on these conditions has been developed. In this study, we review the development of object detection based on deep learning in computer vision. Then, we propose a large-scale publicly available benchmark dataset called object detection for sweeping robots in home scenes (ODSR-IHS). The dataset has 6,000 images and 16,409 instances of 14 object categories. Finally, we evaluate several state-of-the-art methods on the ODSR-IHS dataset and transplant them to the hardware to establish a benchmark dataset for object recognition research on sweeping robots.INDEX TERMS Benchmark dataset, deep learning, hardware, object detection.

No abstract

Aiming at the problems of inaccurate interaction point position, interaction point drift, and interaction feedback delay in the process of LiDAR sensor signal processing interactive system, a target tracking algorithm is proposed by combining LiDAR depth image information with color images. The algorithm first fuses the gesture detection results of the LiDAR and the visual image and uses the color information fusion algorithm of the Camshift algorithm to realize the tracking of the moving target. The experimental results show that the multi-information fusion tracking algorithm based on this paper has achieved higher recognition rate and better stability and robustness than the traditional fusion tracking algorithm.

The accuracy of current deep learning algorithms has certainly increased. However, deploying deep learning networks on edge devices with limited resources is challenging due to their inherent depth and high parameter count. Here, we proposed an improved YOLO model based on an attention mechanism and receptive field (RFA-YOLO) model, applying the MobileNeXt network as the backbone to reduce parameters and complexity, adopting the Receptive Field Block (RFB) and Efficient Channel Attention (ECA) modules to improve the detection accuracy of multi-scale and small objects. Meanwhile, an FPGA-based model deployment solution was proposed to implement parallel acceleration and low-power deployment of the detection algorithm model, which achieved real-time object detection for optical remote sensing images. We implement the proposed DPU and Vitis AI-based object detection algorithms with FPGA deployment to achieve low power consumption and real-time performance requirements. Experimental results on DIOR dataset demonstrate the effectiveness and superiority of our RFA-YOLO model for object detection algorithms. Moreover, to evaluate the performance of the proposed hardware implementation, it was implemented on a Xilinx ZCU104 board. Results of the experiments for hardware and software simulation show that our DPU-based hardware implementation are more power efficient than central processing units (CPUs) and graphics processing units (GPUs), and have the potential to be applied to onboard processing systems with limited resources and power consumption.

No abstract