The DOI matches its Crossref record; 49 of the 49 references it cites were found in a registry or an index.
FPGA Implementation for CNN-Based Optical Remote Sensing Object Detection
Open accessAbstract
In recent years, convolutional neural network (CNN)-based methods have been widely used for optical remote sensing object detection and have shown excellent performance. Some aerospace systems, such as satellites or aircrafts, need to adopt these methods to observe objects on the ground. Due to the limited budget of the logical resources and power consumption in these systems, an embedded device is a good choice to implement the CNN-based methods. However, it is still a challenge to strike a balance between performance and power consumption. In this paper, we propose an efficient hardware-implementation method for optical remote sensing object detection. Firstly, we optimize the CNN-based model for hardware implementation, which establishes a foundation for efficiently mapping the network on a field-programmable gate array (FPGA). In addition, we propose a hardware architecture for the CNN-based remote sensing object detection model. In this architecture, a general processing engine (PE) is proposed to implement multiple types of convolutions in the network using the uniform module. An efficient data storage and access scheme is also proposed, and it achieves low-latency calculations and a high memory bandwidth utilization rate. Finally, we deployed the improved YOLOv2 network on a Xilinx ZYNQ xc7z035 FPGA to evaluate the performance of our design. The experimental results show that the performance of our implementation on an FPGA is only 0.18% lower than that on a graphics processing unit (GPU) in mean average precision (mAP). Under a 200 MHz working frequency, our design achieves a throughput of 111.5 giga-operations per second (GOP/s) with a 5.96 W on-chip power consumption. Comparison with the related works demonstrates that the proposed design has obvious advantages in terms of energy efficiency and that it is suitable for deployment on embedded devices.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures














Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“FPGA is wildly utilized in various tasks including deep learning [199, 247, 331–334].”
From Review of deep learning: concepts, CNN architectures, challenges, applications, future directions (2021) · cites this paper as [332]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.81 · Cited by 32,684
(2016) · Cited by 31,590
Self-citationBatch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S., & Szegedy, C. (2015) · arXiv · doi:10.48550/arxiv.1502.03167 · Cited by 27,818
SSD: Single Shot MultiBox Detector
Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., & Berg, A. C. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46448-0_2 · Cited by 22,128 · cited 4×
“Liu, W.; Anguelov, D.; Erhan, D.; Szegedy, C.; Reed, S.; Fu, C.Y.; Berg, A.C. SSD: Single shot multibox detector.”
MethodInfluentialSelf-citationYOLO9000: Better, Faster, Stronger
Redmon, J., & Farhadi, A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.690 · Cited by 19,892
DOTA: A Large-Scale Dataset for Object Detection in Aerial Images
Xia, G.-S., Bai, X., Ding, J., Zhu, Z., Belongie, S., Luo, J., Datcu, M., Pelillo, M., & Zhang, L. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00418 · Cited by 3,414
Optimizing FPGA-based Accelerator Design for Deep Convolutional Neural Networks
Zhang, C., Li, P., Sun, G., Guan, Y., Xiao, B., & Cong, J. (2015) · Proceedings of the 2015 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays · doi:10.1145/2684746.2689060 · Cited by 2,158 · cited 8×
“FPGAs and ASICs have the advantages of high performance and energy efficiency [16,19].”
BackgroundInfluentialA survey on object detection in optical remote sensing images
Cheng, G., & Han, J. (2016) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2016.03.014 · Cited by 1,475
Joyce, K. E., Belliss, S. E., Samsonov, S. V., McNeill, S. J., & Glassey, P. J. (2009) · Progress in Physical Geography: Earth and Environment · doi:10.1177/0309133309339563 · Cited by 496 · cited 1×
“The increasing volume of image data puts high pressure on the data downlink [8,9].”
BackgroundYOLO9000: Better, Faster, Stronger
Redmon, J., & Farhadi, A. (2016) · arXiv · doi:10.48550/arxiv.1612.08242 · Cited by 488
Cited by
Review of deep learning: concepts, CNN architectures, challenges, applications, future directions
Alzubaidi, L., Zhang, J., Humaidi, A. J., Al-Dujaili, A., Duan, Y., Al-Shamma, O., Santamaría, J., Fadhel, M. A., Al-Amidie, M., & Farhan, L. (2021) · Journal of Big Data · doi:10.1186/s40537-021-00444-8 · Cited by 7,906
FlexCNN: An End-to-end Framework for Composing CNN Accelerators on FPGA
Basalama, S., Sohrabizadeh, A., Wang, J., Guo, L., & Cong, J. (2022) · ACM Transactions on Reconfigurable Technology and Systems · doi:10.1145/3570928 · Cited by 77
Deep Convolutional Neural Networks for Weeds and Crops Discrimination From UAS Imagery
Hashemi-Beni, L., Gebrehiwot, A. A., Karimoddini, A., Shahbazi, A., & Dorbu, F. E. (2022) · Frontiers in Remote Sensing · doi:10.3389/frsen.2022.755939 · Cited by 53
“In recent times, there has been considerable progress in the classi fi cation and segmentation of remote sensing data using deep learning for different applications (Chen et al., 2020 and Zhang et al., 2021).”
MethodA Systematic Literature Review on Binary Neural Networks
Sayed, R., Azmi, H., Shawkey, H., Khalil, A. H., & Refky, M. A. (2023) · IEEE Access · doi:10.1109/access.2023.3258360 · Cited by 61
“INTRODUCTION IN recent years, Convolutional Neural Network (CNN) achieved massive success in various aspects of image classification [1], [2], object recognition [3], [4], object detection [5], speech emotion recognition [6], [7], and classification of noisy non-stationary signals [8].”
BackgroundBrain-Inspired Remote Sensing Interpretation: A Comprehensive Survey
Jiao, L., Huang, Z., Liu, X., Yang, Y., Ma, M., Zhao, J., You, C., Hou, B., Yang, S., Liu, F., et al. (2023) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2023.3247455 · Cited by 49
“Therefore, the authors in [314], [315], and [316] divided the filters into multiple groups for operation.”
BackgroundMessaoud, S., Bouaafia, S., Maraoui, A., Ammari, A. C., Khriji, L., & Machhout, M. (2022) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2021.107671 · Cited by 41
YOLOv4-Tiny-Based Coal Gangue Image Recognition and FPGA Implementation
Xu, S., Yujie, Z., Huang, Y., & Han, T. (2022) · Micromachines · doi:10.3390/mi13111983 · Cited by 36
RAMAN: A Reconfigurable and Sparse tinyML Accelerator for Inference on Edge
Krishna, A., Nudurupati, S. R., Chandana, D., Dwivedi, P., André, V. S., Mehendale, M. M., & Thakur, C. S. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3386832 · Cited by 50
“In addition, several FPGA-based implementations have been proposed in [20], [21], [22], [23], [24], [25], [26], [30], [31], [32], [33], [34], [37], [38], [39], [40], [41], [42], [43], [44], [45], [46], and [47] discussed in detail in Section IV-C.”
BackgroundZhang, Z., Qu, Z., Liu, S., Li, D., Cao, J., & Xie, G. (2022) · Remote Sensing · doi:10.3390/rs14153596 · Cited by 33
High-speed YOLOv4-tiny hardware accelerator for self-driving automotive
Valadanzoj, Z., Daryanavard, H., & Harifi, A. (2023) · The Journal of Supercomputing · doi:10.1007/s11227-023-05713-2 · Cited by 32
“Modified YOLOv2 CNN on Xilinx ZYNQ xc7z035 FPGA was presented in [33].”
FPGA-Based Implementation of Ship Detection for Satellite On-Board Processing
Xu, M., Chen, L., Shi, H., Yang, Z., Li, J., & Long, T. (2022) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2022.3218440 · Cited by 28
“In order to achieve the processing on-board, the algorithms need to be implemented on embedded processors, such as field programmable gate array (FPGA) [5], [6], [7], [8], [9], [10], [11], [12], digital signal processors (DSP) [3], [4], and GPU [1], [2].”
BackgroundMethodInfluentialResource-constrained FPGA implementation of YOLOv2
Zhang, Z., Mahmud, M. A. P., & Kouzani, A. Z. (2022) · Neural Computing and Applications · doi:10.1007/s00521-022-07351-w · Cited by 25
“Since the reports from Vivado are considered in the majority of existing publications [21, 34, 35], we consider the resource utilization, in terms of on-chip memory, DSPs, LUTs, and FFs reported in Vivado, and the power consumption, i.e. the total on-chip power, reported from the power analyser of…”
BackgroundYan, T., Zhang, N., Li, J., Liu, W., & Chen, H. (2022) · Remote Sensing · doi:10.3390/rs14133130 · Cited by 30
Self-citationAll Adder Neural Networks for On-Board Remote Sensing Scene Classification
Zhang, N., Wang, G., Wang, J., Chen, H., Liu, W., & Chen, L. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3267445 · Cited by 28
“In traditional remote sensing, remote sensing images are first downloaded from satellites to ground stations and then interpreted and analyzed to perform RSSC [8], [9].”
MethodSelf-citationA review of image-based deep learning methods for crack detection
Pandey, V., & Mishra, S. S. (2025) · Multimedia Tools and Applications · doi:10.1007/s11042-025-20729-x · Cited by 32
“Some more papers are given by Zhang et al., 2021 [20] ; Nguyen et al., 2022 [21] and Li et al., 2022 [16] .”
State of the Art: High-Performance and High-Throughput Computing for Remote Sensing Big Data
Zhang, S., Xue, Y., Zhou, X., Zhang, X., Liu, W., Li, K., & Liu, R. (2022) · IEEE Geoscience and Remote Sensing Magazine · doi:10.1109/mgrs.2022.3204590 · Cited by 21
“Zhang et al. [221] implemented an improved YOLO v2 remote sensing image target detection method on an FPGA and designed a collaborative hardware/ software framework with good universality and flexibility.”
MethodSelf-citationFeSHI: Feature Map-Based Stealthy Hardware Intrinsic Attack
Odetola, T. A., Khalid, F., Mohammed, H., Sandefur, T., & Hasan, S. R. (2021) · IEEE Access · doi:10.1109/access.2021.3104520 · Cited by 15
Fata, J. S., Elmannai, W., & Elleithy, K. M. (2025) · IEEE Access · doi:10.1109/access.2025.3594348 · Cited by 15
Pflow: An end-to-end heterogeneous acceleration framework for CNN inference on FPGAs
Wan, Y., Xie, X., Yi, L., Jiang, B., Chen, J., & Jiang, Y. (2024) · Journal of Systems Architecture · doi:10.1016/j.sysarc.2024.103113 · Cited by 20
Integrating physiological signals for enhanced sleep apnea diagnosis with SleepNet
Hemrajani, P., Dhaka, V. S., Rani, G., Verma, S., Kavita, Woźniak, M., Shafi, J., & Ijaz, M. F. (2025) · Scientific Reports · doi:10.1038/s41598-025-16154-7 · Cited by 15
“Innovative strategies, such as the reversed-pruning method by 23 and network optimizations by 24 , highlight ongoing efforts to improve the efficiency and effectiveness of SA detection models.”
Ni, S., Wei, X., Zhang, N., & Chen, H. (2023) · Remote Sensing · doi:10.3390/rs15245784 · Cited by 15
Self-citationWang, G., Wan, G., Su, Z., Wang, Y., Jia, Y., Li, G., & Liang, S. L. (2025) · IEEE Access · doi:10.1109/access.2025.3573932 · Cited by 21
Wang, G., Chen, H., & Xie, Y. (2021) · Electronics · doi:10.3390/electronics10060662 · Cited by 11
Self-citationRecent advances in Machine Learning based Advanced Driver Assistance System applications
Tatar, G., Bayar, S., Çiçek, İ., & Niar, S. (2024) · Microprocessors and Microsystems · doi:10.1016/j.micpro.2024.105101 · Cited by 13
Xie, Y.-L., & Lin, C. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.125691 · Cited by 14
Ahmed, T. S., Sayed, A. N., Youssef, A. M. M., Shaker, G. S. A., & Elbahnasawy, M. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3566651 · Cited by 10
“This is in contrast to (3 × 3) pooling, which can lose fine details, and (8 × 8) pooling, which greatly reduces resolution [37].”
A deep relearning method based on the recurrent neural network for land cover classification
Tang, Y., Qiu, F., Wang, B., Wu, D., Jing, L., & Sun, Z. (2022) · GIScience & Remote Sensing · doi:10.1080/15481603.2022.2115589 · Cited by 13
“Second, the CNN and related methods are more suited for scene understanding (Zhang et al. 2018a; Khan et al. 2019) and object recognition (Ren, Zhu, and Xiao 2018; Zhang et al. 2021), as the underlying features and spatial contextual information are more obvious for a typical scene or object.”
MethodHardware Design of Lightweight Binary Classification Algorithms for Small-Size Images on FPGA
Saglam, S., & Bayar, S. (2024) · IEEE Access · doi:10.1109/access.2024.3390564 · Cited by 9
Research on map emotional semantics using deep learning approach
Xi, D., Hu, X., Yang, L., Yang, N., Liu, Y., & Jiang, H. (2023) · Cartography and Geographic Information Science · doi:10.1080/15230406.2023.2172081 · Cited by 9
“Outstanding break-throughs have been made in many computer vision tasks, such as image segmentation (Alam et al., 2021), image classification (H. Gong et al., 2021), and object detection (N. Zhang et al., 2021).”
A Fast and Low-Power Detection System for the Missing Pin Chip Based on YOLOv4-Tiny Algorithm
Chen, S., Lai, W., Ye, J., & Ma, Y. (2023) · Sensors · doi:10.3390/s23083918 · Cited by 8
FPGA Implementation of Image Registration Using Accelerated CNN
Aydın, S. G., & Bılge, H. Ş. (2023) · Sensors · doi:10.3390/s23146590 · Cited by 10
“In [36], an FPGA-based CNN implementation was considered for object detection in optical remote sensing.”
MethodMotion-Based Object Location on a Smart Image Sensor Using On-Pixel Memory
Valenzuela, W. E., Saavedra, A., Zarkesh-Ha, P., & Figueroa, M. E. (2022) · Sensors · doi:10.3390/s22176538 · Cited by 9
“In recent years, many FPGA-based Convolutional Neural Network (CNN) architectures have been proposed for object location and classification [46–50].”
BackgroundOptimizing FPGA-based YOLO series accelerators: A survey of techniques
Chua, W. H., Uttraphan, C., Choon, C. C., & Ching, K. B. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.130874 · Cited by 12
Hardware Acceleration of Satellite Remote Sensing Image Object Detection Based on Channel Pruning
Zhao, Y., Lv, Y., & Li, C. (2023) · Applied Sciences · doi:10.3390/app131810111 · Cited by 13
Xue, L., Wang, X., Wang, Z., Li, G., Song, H., & Song, Z. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3398820 · Cited by 8
“In most of the existing CD systems, remote sensing images captured by satellites are first downloaded to ground stations and then processed and analyzed to perform CD [12], [13].”
MethodAutomatic detection method of small target in tennis game video based on deep learning
Gao, D., Zhang⋆, Y., & Qiu, H. (2023) · Journal of Intelligent & Fuzzy Systems · doi:10.3233/jifs-231167 · Cited by 6
“In the process of fine segmentation, the detection result of sub block region growth algorithm and the original video image are used as the input of SRG grab cut algorithm [19].”
An Efficient Ensemble Binarized Deep Neural Network on Chip with Perception-Control Integrated
He, W., Yang, D., Peng, H., Liang, S., & Lin, Y. (2021) · Sensors · doi:10.3390/s21103407 · Cited by 7
“Zhao [49] Cho [40] Zhang [50] Lu [35] Li [51] Ours”
BackgroundMethodInfluentialAdaCB: An Adaptive Gradient Method with Convergence Range Bound of Learning Rate
Liao, X., Sahran, S., Abdullah, A., & Shukor, S. A. (2022) · Applied Sciences · doi:10.3390/app12189389 · Cited by 5
A novel multiplier-less convolution core for YOLO CNN ASIC implementation
Bagherzadeh, S., Daryanavard, H., & Semati, M. R. (2024) · Journal of Real-Time Image Processing · doi:10.1007/s11554-024-01419-7 · Cited by 5
“ASIC implementation has the advantages of high performance and ultra-low power consumption [16]; however, it requires a long development period and increased costs for design and implementation.”
Teboulbi, S., Messaoud, S., Hajjaji, M. A., Mtibaa, A., & Atri, M. (2024) · Signal Image and Video Processing · doi:10.1007/s11760-024-03177-2 · Cited by 8
Transmission line fault detection using deep learning technique
Hlalele, T. S. (2024) · International Conference on Advances in Artificial Intelligence (ICAAI) · doi:10.1145/3704137.3704170 · Cited by 7
“The paper suggests an effective hardware-implementation method for optical remote-sensing object detection [15].”
A Versatile Systolic Array for Transposed and Dilated Convolution on FPGA
Basalama, S., Sohrabizadeh, A., Wang, J., & Cong, J. (2022) · IEEE International Symposium on Field-Programmable Custom Computing Machines (FCCM) · doi:10.1109/fccm53951.2022.9786198 · Cited by 5
A service-oriented framework for remote sensing big data processing
Enayati, R., Ravanmehr, R., & Aghazarian, V. (2023) · Earth Science Informatics · doi:10.1007/s12145-022-00900-w · Cited by 5
“Zhang et al. proposed the implementation of FPGA to detect optical objects based on convolutional neural networks (CNN) (Zhang et al. 2021).”
BackgroundDereli, S., & Ünsal, A. R. (2023) · Microprocessors and Microsystems · doi:10.1016/j.micpro.2023.104908 · Cited by 7
Zhang, Y., Ma, C., Li, Z., & Li, J. (2023) · Electronics · doi:10.3390/electronics12092132 · Cited by 6
Design and Implementation of a YOLOv2 Accelerator on a Zynq-7000 FPGA
Kim, H. W., & Kim, T.-K. (2025) · Sensors · doi:10.3390/s25206359 · Cited by 8
Low-Cost FPGA-Enhanced CNN Accelerator for Real-Time YOLO Object Detection and Classification
Fata, J. S., & Elmannai, W. (2026) · IEEE Access · doi:10.1109/access.2026.3669451 · Cited by 5
An Efficient On-Chip Data Storage and Exchange Engine for Spaceborne SAR System
Lv, H., Li, Y., Xie, Y., & Qiao, T. (2023) · Remote Sensing · doi:10.3390/rs15112885 · Cited by 4
Zhang, N., Ni, S., Qiao, T., Liu, W., & Chen, H. (2023) · International Conference on Field-Programmable Technology (FPT) · doi:10.1109/icfpt59805.2023.00036 · Cited by 4
“In traditional remote sensing, remote sensing images are first downloaded from satellites to ground stations to perform RSSC [2].”
MethodSelf-citationThe Proposition of Three Approaching Ways to Implement Tan-sigmoid Activation Function in FPGA
Ali, M., & Abed, B. H. (2022) · Engineering and Technology Journal · doi:10.30684/etj.v40i2.2160 · Cited by 4
“[19] proposed an efficient hardware implementation system to identify objects for optical remote sensing.”
MethodLomas-Barrié, V., Silva-Flores, R., Neme, A., & Peña‐Cabrera, M. (2022) · Electronics · doi:10.3390/electronics11050696 · Cited by 3
Fast-Pipe: Efficient Multi-Channel Data Mapping on Edge FPGAs for Satellite Remote Sensing
Shu, C., Qi, B., Sun, Y., & Wang, K. (2022) · Globecom · doi:10.1109/globecom48099.2022.10000908 · Cited by 3
“However, with the development of remote sensing technology, the resolution and the data amount of optical remote sensing images are constantly increasing, which leads to huge latency [1].”
BackgroundMethodInfluentialZhang, C., Liu, X., Shang, Q., Wu, C., Wang, Y., Wang, L., Zhang, X., Liang, F., & Luo, L. (2025) · Infrared Physics & Technology · doi:10.1016/j.infrared.2025.106015 · Cited by 3
Deep CNN Co-design for HEVC CU Partition Prediction on FPGA–SoC
Bouaafia, S., Khemiri, R., Messaoud, S., & Sayadi, F. E. (2022) · Neural Processing Letters · doi:10.1007/s11063-022-10765-1 · Cited by 3
“[29]proposed aCNN-basedremotesensingobjectdetectionalgorithm.”
MethodA Resource Efficient CNN Accelerator for Sensor Signal Processing Based on FPGA
Wu, R., Liu, B., Fu, P., & Chen, H. (2022) · Journal of Circuits Systems and Computers · doi:10.1142/s0218126623500755 · Cited by 3
Self-citationAccelerated and optimized covariance descriptor for pedestrian detection in self-driving cars
Abid, N., Ammari, A. C., Maashri, A. A., Abid, M., & Awadalla, M. H. A. (2023) · Design Automation for Embedded Systems · doi:10.1007/s10617-023-09273-9 · Cited by 3
“In [50], Zhang et al. developed a hardware implementation of YOLOv2 CNN-based object detection targeting Xilinx ZYNQ xc7z035 platform.”
MethodResultImproving Seed-Based FPGA Packing with Indirect Connection for Realization of Neural Networks
Yu, L., Guo, B., Zhi, T., & Bai, L. (2023) · Electronics · doi:10.3390/electronics12122691 · Cited by 3
“NN applications such as image classification [1], object detection [2], and natural language processing [3] can take full advantage of the reconfigurable parallelism of FPGA architectures.”
BackgroundScale-Frequency Dual-Modulation Method for Remote Sensing Image Continuous Super-Resolution
Gao, S., Wang, G., Xie, B., Wei, X., Wang, J., & Liu, W. (2024) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2024.3483991 · Cited by 2
“I N RECENT years, remote sensing (RS) images have played an important role in the fields such as smart agriculture [1], emergency management [2], public safety [3], and resource exploration[4],[5],[6],[7],[8],[9].”
BackgroundSelf-citationA DSP–FPGA Heterogeneous Accelerator for On-Board Pose Estimation of Non-Cooperative Targets
Song, Q. W., Liu, K., Li, S., Wang, M., & Wang, J. (2025) · Aerospace · doi:10.3390/aerospace12070641 · Cited by 2
Kumar, A. R., Гаур, Н., & Nanthaamornphong, A. (2025) · IET Communications · doi:10.1049/cmu2.70117 · Cited by 2
Designing of Intelligent Hardware System for Brain Tumor Detection
Mallick, A., Ghosh, S., Banerjee, S., Maji, P., & Mondal, H. K. (2025) · IEEE India Council International Subsections Conference (INDISCON) · doi:10.1109/indiscon66021.2025.11254970 · Cited by 2
“CNN-based object detection for optical remote sensing, focusing on energy efficiency and performance optimization in [7] was evaluated using YOLOv2 on a Xilinx ZYNQ xc7z035 FPGA that achieved high computational efficiency with minimal accuracy loss compared to GPU implementations.”
Improved YOLO for fabric defect detection algorithm deployment based on FPGA
Xiang, H., Zhen, W., Huang, Z., Li, B., & Li, C. (2025) · Journal of Real-Time Image Processing · doi:10.1007/s11554-025-01820-w · Cited by 2
“For example, Zhang et al. [15] used FPGAs to implement CNN for traffic light classification and Nguyen et al. [16] used FPGAs to implement high-throughput YOLO model deployment, while Zhang et al. [17] used FPGAs to deploy object detection models for optical remote sensing object detection.”
Wang, Q., Wen, Q., Wei, Z., Mao, H., Tao, R., & Zhang, H. (2026) · Intelligent Marine Technology and Systems · doi:10.1007/s44295-026-00098-3 · Cited by 2
Lu, A., Hu, Y., Cao, Z., Liu, J., Li, L., & Li, Z. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3526142 · Cited by 2
FPGA Based AI Inference Accelerator for Low-End Embedded Systems
Premalatha, S., NandhaKumar, R., Marthandan, T., Logeshwaran, R., Dharmasastha, P., & Sivaperumal, K. (2025) · International Conference on Artificial Intelligence and Machine Learning Applications Theme: Healthcare and Internet of Things (AIMLA) · doi:10.1109/aimla63829.2025.11040308 · Cited by 5
“It does these computations parallelly and be used for tasks requiring low power, low memory & real-time process [5].”
Huang, J., Li, Z., Yu-xian, J., Zhang, Z., Wang, H., & Chang, S. (2025) · IEEE Transactions on Computers · doi:10.1109/tc.2025.3585354 · Cited by 3
“Reference [40] and [41] are typical PE architectures.”
Routability-aware Packing for High-density Nonvolatile FPGAs
Zheng, H., Xiong, Y., Zuo, J., Zhang, H., Jia, Z., & Zhao, M. (2025) · ACM/IEEE Design Automation Conference (DAC) · doi:10.1109/dac63849.2025.11133374 · Cited by 1
“Field-programmable gate array (FPGA) is a promising option for many emerging applications, including near memory computing [1], [2], computer vision [3], [4], data encryption [5], [6], and large language model [7], [8], due to its high parallelism and reconfigurable flexibility.”
FPGA-Based Neural Network Accelerators for Space Missions: A Survey
Antunes, P., & Podobas, A. (2026) · ACM Computing Surveys · doi:10.1145/3857797 · Cited by 11
Karımzadeh, S., Ghasemi, M., Matsuoka, M., Zülfikar, A. C., Miura, H., & Fahjan, Y. (2026) · Advances in Space Research · doi:10.1016/j.asr.2026.06.009 · Cited by 1
FPGA-based implementations– A Review
Jalaja, G. S., Mr. Praveen, M., & Kurian, M. Z. (2022) · IJIREEICE · doi:10.17148/ijireeice.2022.10231 · Cited by 1
“[2] With the advancements in Machine Learning, Convolutional Neural Network based techniques have been used in remote object detection and sensing.”
Medetov, B., Serikov, T., Tolegenova, A., Zhexebay, D., Yskak, A., Namazbayev, T. A., & Albanbay, N. (2023) · Eastern-European Journal of Enterprise Technologies · doi:10.15587/1729-4061.2023.281731 · Cited by 1
“The paper [5] presents the results of studies of the hardware implementation of the YOLOv2 model on the Xilinx ZYNQ xc7z035 FPGA for object detection.”
MethodSurvey on object detection in VLSI architecture through deep learning
Francis, N. C., & Mathana, J. M. (2024) · AIP conference proceedings · doi:10.1063/5.0209400 · Cited by 2
Efficient Modulation Format Identification Engine with CNN on FPGA
Li, H. Y., Lu, Y., Zeng, Q., Wen, Y., & Kong, Y. (2025) · IEEE Joint International Information Technology and Artificial Intelligence Conference (ITAIC) · doi:10.1109/itaic64559.2025.11163048 · Cited by 2
“Recent studies have shown that when designing CNN accelerators for image recognition on FPGA, these accelerators outperform frequency domain methods [18-20].”
Efficient Hardware Optimization for CNN
Aydın, S. G., & Bılge, H. Ş. (2022) · International Journal of Multidisciplinary Studies and Innovative Technologies · doi:10.36287/ijmsit.6.1.38 · Cited by 2
“Researchers in [8] used implemented YOLO2 on FPGA for optical remote sensing.”
MethodWang, Y., Feng, W., Yu, C., Hu, X., & Zhang, Y. (2022) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc55256.2022.10034010
“[17] proposed a general processing engine (PE) to deploy a modified YOLOv2 network on a Xilinx ZYNQ xc7z035 FPGA.”
MethodGuo, Y., Duan, S., & Wang, L. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-4399-5_41
Zhu, Z., Liu, J., Wang, Y., Luo, S., Fu, C., Liang, M.-F., Luo, L., & Liang, F. (2024) · IEEE Sensors Letters · doi:10.1109/lsens.2024.3497148
“We applied it to the recognition detection of standard Chinese character radicals, using a heterogeneous combination of MCU,field-programmablegatearray(FPGA)[16],[17],andadvanced RISC machine (ARM) for the classification detection task.”
Global Information Edge Augmentation Network for Remote Sensing Image Continuous Super-Resolution
Gao, S., Lei, Y. L., Zhang, J., Wang, G., & Liu, W. (2024) · IEEE International Conference on Signal, Information and Data Processing (ICSIDP) · doi:10.1109/icsidp62679.2024.10869153
“In recent years, remote sensing (RS) images have been extensively utilized in an ever-growing range of fields [1]–[5].”
Self-citationHardware implementation of SNN-Based
Dong, H., Li, J., Lan, B., Xu, M., & Chen, L. (2024) · Asia Symposium on Image and Graphics (ASIG) · doi:10.1145/3718441.3718451
Performance Assessment of Object Detection for Military Vehicles in Complex Visual Environments
Hildebrand, F. K., Schnell, M. K., Bachmann, E., & Sahutoglu, Z. (2025) · International Conference on Electrical Engineering, Computing Science and Automatic Control (CCE) · doi:10.1109/cce67728.2025.11271927
“For instance, in the development of unmanned aerial vehicles (UAVs), object detection is a critical component for navigation, obstacle avoidance, and mission execution [14].”
Optimized Neural Network Hardware Accelerator for Object Detection Based on Zynq
Luo, C., Li, J., & Sun, K. (2025) · UK-Europe-China Workshop on Millimetre Waves and Terahertz Technologies (UCMMT) · doi:10.1109/ucmmt67044.2025.11286759
“Our accelerator targets YOLOv3-tiny network, which has deep layers and large parameter quantities [8].”
CNN Architectures on FPGA for Maritime Object Detection: A Review of Methods and Challenges
Haijoub, A., Hatim, A., González, A. G., Srifi, M. N., & Arioua, M. (2025) · International Symposium on Advanced Electrical and Communication Technologies (ISAECT) · doi:10.1109/isaect68904.2025.11318704 · Cited by 1
“Finally, aggressive compression (e.g., INT4 and > 30 – 50 % structured pruning) should be validated explicitly on small-boat subsets to ensure long-range recall is maintained [15], [33], [34].”
InfluentialFPGA-Based Artificial Intelligence Accelerator for On-Board Processing of Aerial Scenes
AbdElkarim, O., Sherif, S., Inoue, K., Zewail, R., & Sayed, M. S. (2025) · doi:10.1109/icm66518.2025.11322530
Video compression of airplane cockpit screens content
Mitrica, I. (2021) · theses.fr (ABES) · doi:10.70675/18512bbdzfb2fz4993zaecfz8a0e94302a12 · Cited by 1
Bocchi, T., Pacini, T., Nannipieri, P., Zulberti, L., Kiliç, A., Moranti, S., & Fanucci, L. (2026) · IEEE Aerospace and Electronic Systems Magazine · doi:10.1109/maes.2026.3693162
“Zhang et al. [16] introduced a hardware implementation of an improved you only look once (YOLO)v2 network on a Zynq 7000 SoC, which achieved a 33.4-fold improvement in energy efficiency over CPU implementations, consuming only 5.96 W with negligible accuracy loss compared to GPU solutions.”
Influential
Metadata
- Authors
- Zhang, N., Wei, X., Chen, H., & Liu, W.
- Affiliations
- Beijing Institute of Technology (CN)
- Tsinghua University (CN)
- Corresponding author
- Liu, Wenchao
- Venue
- Electronics
- Publisher
- MDPI AG
- Published
- 2021-01-25
- Volume
- 10
- Issue
- 3
- Pages
- 282
- ISSN
- 2079-9292 (ISSN-L)
- OpenAlex
- W3121787284
- Cited by
- 85
- References
- 46
- Citations by year
- 2026: 5 · 2025: 21 · 2024: 15 · 2023: 18 · 2022: 21 · 2021: 5
- FWCI
- 5.31
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Electronics (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- National Key R & D Program of China (2017YFB0502800, 2017YFB0502804)
- the MYHT Program of China (B0201)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Hardware and Architecture › Embedded Systems Design Techniques
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Embedded Systems and FPGA Applications
- Keywords
- FPGA implementation, convolutional neural networks, optical remote sensing, object detection, YOLOv2, hardware architecture, energy efficiency, embedded systems, Xilinx Zynq
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.