LCLi Cheng

Li Cheng

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Li Cheng has a total of 14 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • A Programmable and Flexible Vision Processor

    by Qian Luo, Chunhe Yao, Ke Ning, Xuemin Zheng, Mingxin Zhao, Li Cheng, Shuangming Yu, Jian Liu, Nanjian Wu, Liyuan Liu

    Vision chips perform image capture and real-time intelligent image processing by integrating an imager and a vision processor on a single chip, having broad application prospects. This brief proposes a programmable and flexible vision processor with a dual-issue micro-architecture. The processor consists of a reconfigurable vector unit, a flexible memory access network, and a non-maximum suppression (NMS) block. It can efficiently implement both deep neural network (DNN) and traditional computer vision (CV) algorithms. The vector unit performs single-instruction multiple-vector (SIMV) parallel operations with reconfigurable vector width. The flexible memory access network adaptively supports multiple vector operations under different vector widths. A four-MAC processing element (PE) in the vector unit is designed to increase computational power and data reuse rate. The NMS block can speed up the object location processing of the detection networks. The chip is fabricated in a 28nm process. The experimental results show that the maximum clock frequency, peak performance, and peak energy efficiency are 600MHz, 1.2TOPS, and 2.03TOPS/W, respectively. The Mobilenet-V1 processing achieves a throughput of 404 fps under a $256\times 224$ image size and an 87.15%(top-5) accuracy on the ImageNet dataset.


  • ViP: A Hierarchical Parallel Vision Processor for Hybrid Vision Chip

    by Xuemin Zheng, Li Cheng, Mingxin Zhao, Qian Luo, Honglong Li, Runjiang Dou, Shuangming Yu, Nanjian Wu, Liyuan Liu

    Nowadays, the vision chip bridging sensing and processing has been extensively employed in high-speed image processing, owing to its excellent performance, low power consumption, and economical cost. However, there is a dilemma in designing processors to support conventional computer vision algorithms and neural networks since the two algorithms have a non-trivial trade-off in proposing a unified architecture. By analyzing computation properties, we propose a novel hierarchical parallel vision processor (ViP) for hybrid vision chips to accelerate both traditional computer vision (CV) and neural network (NN). The ViP architecture includes three parallelism levels: PE for pixel-centric, computing core (CC) for block, and vision core (VC) for global. PEs contain dedicated computing units and data paths for convolution operations without degrading its flexibility. Each CC is driven by customized SIMD instructions and can be dynamically connected for meeting block parallelism requirements. ViP is fabricated in 65nm CMOS technology and achieves a peak performance of 614.4 GOPS and an energy efficiency of 640 GOPS/W at 200 MHz clock frequency. Notably, several experiments on CV and NN are performed, illustrating an ultra-low latency in executing hybrid algorithms.


  • A Provisional Labels-Reduced, Real-Time Connected Component Labeling Algorithm for Edge Hardware

    by Hongtao Zhou, Runjiang Dou, Li Cheng, Jian Liu, Nanjian Wu

    Connected component labeling (CCL) is an important operation in computer vision tasks, widely used for real-time image processing on edge hardware. The existing connected component labeling algorithms always generate plenty of provisional labels. Solving the equivalence of provisional labels needs much memory access and processing time. The greater difficulty is that the processing time varies with the number and shape of the connected components. To solve the problems, this brief proposes a new two-scan CCL algorithm. It consists of novel provisional label predicting and provisional label assignment methods based on predicting table, linked lists, and equivalent table. The provisional label predicting method reduces the number of provisional labels effectively. The provisional label assignment method can implement quickly the assignment operation of CCL by combination of the first scan and the second scan with fixed processing time. We have implemented the proposed algorithm on Field Programmable Gate Arrays (FPGA) for raster scan images. The results show that its processing speed can achieve 726fps@225MHz for $640\times 480$ image resolution, and its resource utilization is less than 15% of compared implementation. It is suitable for real-time edge applications. Compared with other algorithms, the proposed algorithm reduces provisional labels efficiently and completes the CCL operation with a fixed number of iterations. Therefore, it shortens processing time and makes the processing time constant.


  • Open Access

    SiamMixer: A Lightweight and Hardware-Friendly Visual Object-Tracking Network

    by Li Cheng, Xuemin Zheng, Mingxin Zhao, Runjiang Dou, Shuangming Yu, Nanjian Wu, Liyuan Liu

    Siamese networks have been extensively studied in recent years. Most of the previous research focuses on improving accuracy, while merely a few recognize the necessity of reducing parameter redundancy and computation load. Even less work has been done to optimize the runtime memory cost when designing networks, making the Siamese-network-based tracker difficult to deploy on edge devices. In this paper, we present SiamMixer, a lightweight and hardware-friendly visual object-tracking network. It uses patch-by-patch inference to reduce memory use in shallow layers, where each small image region is processed individually. It merges and globally encodes feature maps in deep layers to enhance accuracy. Benefiting from these techniques, SiamMixer demonstrates a comparable accuracy to other large trackers with only 286 kB parameters and 196 kB extra memory use for feature maps. Additionally, we verify the impact of various activation functions and replace all activation functions with ReLU in SiamMixer. This reduces the cost when deploying on mobile devices.


  • Open Access

    TBC-Net: A real-time detector for infrared small target detection using semantic constraint

    by Mingxin Zhao, Li Cheng, Xu Yang, Peng Feng, Liyuan Liu, Nanjian Wu

    Infrared small target detection is a key technique in infrared search and tracking (IRST) systems. Although deep learning has been widely used in the vision tasks of visible light images recently, it is rarely used in infrared small target detection due to the difficulty in learning small target features. In this paper, we propose a novel lightweight convolutional neural network TBC-Net for infrared small target detection. The TBCNet consists of a target extraction module (TEM) and a semantic constraint module (SCM), which are used to extract small targets from infrared images and to classify the extracted target images during the training, respectively. Meanwhile, we propose a joint loss function and a training method. The SCM imposes a semantic constraint on TEM by combining the high-level classification task and solve the problem of the difficulty to learn features caused by class imbalance problem. During the training, the targets are extracted from the input image and then be classified by SCM. During the inference, only the TEM is used to detect the small targets. We also propose a data synthesis method to generate training data. The experimental results show that compared with the traditional methods, TBC-Net can better reduce the false alarm caused by complicated background, the proposed network structure and joint loss have a significant improvement on small target feature learning. Besides, TBC-Net can achieve real-time detection on the NVIDIA Jetson AGX Xavier development board, which is suitable for applications such as field research with drones equipped with infrared sensors.