YOLO-GD: A Deep Learning-Based Object Detection Algorithm for Empty-Dish Recycling Robots

IEEE Trans. Instrum. Meas.

Meng

2023

Self Cite

The emergence of empty-dish recycling robots has alleviated problems, such as labor shortages, caused by an aging population. The detection and grasping of dishes play a crucial role in empty-dish recycling robots. However, due to the limited resources of edge devices, traditional object detection models require more space to store parameters and much computational overhead, limiting the development of empty-dish recycling robots. Therefore, this article proposes an ultralightweight dish detection model YOLO-GS for an empty-dish recycling robot. We use the modified CSPDarknet as the backbone structure and design an ultralightweight neck structure for efficient feature fusion. Meanwhile, we design a lightweight head structure for object classification and bounding box coordinate regression by combining ghost shuffle convolution (GSConv2D) and the anchor-free method. For the empty-dish recycling robot to grasp the dishes, we design a dish grasp point extraction algorithm using image processing. Finally, TensorRT is used to optimize and accelerate the model for efficient and intelligent detection of dishes on the NVIDIA Jetson Xavier NX. The experimental results show that YOLO-GS achieves 99.380% mean average precision (mAP) with a parameter amount of 0.606 M. The inference speed of the TensorRT-optimized YOLO-GS algorithm reaches 31.371 FPS, which meets the needs of real-time dish detection by the empty-dish recycling robot. The image of the empty-dish recycling robot demo is available at https://www.youtube.com/watch?v=pCBo1nzm3qU&t=22s.

Section: A Overview Of Empty-dish Recycling Robotmentioning

confidence: 99%

Section: A Experimental Configurations 1) Implementation Detailsmentioning

confidence: 99%

See 1 more Smart Citation

An Ultralightweight Object Detection Network for Empty-Dish Recycling Robots

IEEE Trans. Instrum. Meas.

Meng

2023

Self Cite

“…DNNs have been widely applied in various domains with excellent performance, including computer vision (Ozaki and Kuroda 2021;Xie et al 2021;Yue et al 2022;Meng et al 2018), self-driving vehicles (Cardoso et al 2020;Chernikova et al 2019), natural language processing (Otter et al 2021;Chai et al 2021;Lin et al 2022), cultural heritage preservation (Chen 2021;Fujikawa etal. 2022), human healthcare (Zhang et al 2020;Chen et al 2020;Xiang et al 2021;Zhang et al 2021;Pokaprakarn et al 2022;, etc.…”

Section: Introductionmentioning

confidence: 99%

An architecture-level analysis on deep learning models for low-impact computations

Wang

et al. 2022

Artif Intell Rev

Self Cite

Deep neural networks (DNNs) have made significant achievements in a wide variety of domains. For the deep learning tasks, multiple excellent hardware platforms provide efficient solutions, including graphics processing units (GPUs), central processing units (CPUs), field programmable gate arrays (FPGAs), and application-specific integrated circuit (ASIC). Nonetheless, CPUs outperform other solutions including GPUs in many cases for the inference workload of DNNs with the support of various techniques, such as the high-performance libraries being the basic building blocks for DNNs. Thus, CPUs have been a preferred choice for DNN inference applications, particularly in the low-latency demand scenarios. However, the DNN inference efficiency remains a critical issue, especially when low latency is required under conditions with limited hardware resources, such as embedded systems. At the same time, the hardware features have not been fully exploited for DNNs and there is much room for improvement. To this end, this paper conducts a series of experiments to make a thorough study for the inference workload of prominent state-of-the-art DNN architectures on a single-instruction-multiple-data (SIMD) CPU platform, as well as with widely applicable scopes for multiple hardware platforms. The study goes into depth in DNNs: the CPU kernel-instruction level performance characteristics of DNNs including branches, branch prediction misses, cache misses, etc, and the underlying convolutional computing mechanism at the SIMD level; The thorough layer-wise time consumption details with potential time-cost bottlenecks; And the exhaustive dynamic activation sparsity with exact details on the redundancy of DNNs. The research provides researchers with comprehensive and insightful details, as well as crucial target areas for optimising and improving the efficiency of DNNs at both the hardware and software levels.

“…Deep neural networks (DNNs) have achieved great success in various domains, including object detection ( Yue et al, 2022b ; Dong et al, 2022 ), natural language processing, human health care ( Saho et al, 2022 ; Chen et al, 2020 ), cultural heritage protection ( Yue et al, 2022a ; Fujikawa et al, 2022 ), and intelligent control ( Li et al, 2020 ; Liu, Yu & Cang, 2018 , 2019 ; Liu et al, 2020 ), etc. However, the convolution operation extracts specific data rather than generalized data, which are sensitive to the location of the input feature maps.…”

Section: Introductionmentioning

confidence: 99%

Enhanced mechanisms of pooling and channel attention for deep learning feature maps

Meng

2022

PeerJ Computer Science

Self Cite

The pooling function is vital for deep neural networks (DNNs). The operation is to generalize the representation of feature maps and progressively cut down the spatial size of feature maps to optimize the computing consumption of the network. Furthermore, the function is also the basis for the computer vision attention mechanism. However, as a matter of fact, pooling is a down-sampling operation, which makes the feature-map representation approximately to small translations with the summary statistic of adjacent pixels. As a result, the function inevitably leads to information loss more or less. In this article, we propose a fused max-average pooling (FMAPooling) operation as well as an improved channel attention mechanism (FMAttn) by utilizing the two pooling functions to enhance the feature representation for DNNs. Basically, the methods are to enhance multiple-level features extracted by max pooling and average pooling respectively. The effectiveness of the proposals is verified with VGG, ResNet, and MobileNetV2 architectures on CIFAR10/100 and ImageNet100. According to the experimental results, the FMAPooling brings up to 1.63% accuracy improvement compared with the baseline model; the FMAttn achieves up to 2.21% accuracy improvement compared with the previous channel attention mechanism. Furthermore, the proposals are extensible and could be embedded into various DNN models easily, or take the place of certain structures of DNNs. The computation burden introduced by the proposals is negligible.