Real-Time Apple Detection System Using Embedded Systems With Hardware Accelerators: An Edge AI Application
Open accessThe DOI matches its Crossref record; 56 of the 59 references it cites were found in a registry or an index.
Abstract
Real-time apple detection in orchards is one of the most effective ways of estimating apple yields, which helps in managing apple supplies more effectively. Traditional detection methods used highly computational machine learning algorithms with intensive hardware set up, which are not suitable for infield real-time apple detection due to their weight and power constraints. In this study, a real-time embedded solution inspired from “Edge AI” is proposed for apple detection with the implementation of YOLOv3-tiny algorithm on various embedded platforms such as Raspberry Pi 3 B+ in combination with Intel Movidius Neural Computing Stick (NCS), Nvidia's Jetson Nano and Jetson AGX Xavier. Data set for training were compiled using acquired images during field survey of apple orchard situated in the north region of Italy, and images used for testing were taken from widely used google data set by filtering out the images containing apples in different scenes to ensure the robustness of the algorithm. The proposed study adapts YOLOv3-tiny architecture to detect small objects. It shows the feasibility of deployment of the customized model on cheap and power-efficient embedded hardware without compromising mean average detection accuracy (83.64%) and achieved frame rate up to 30 fps even for the difficult scenarios such as overlapping apples, complex background, less exposure of apple due to leaves and branches. Furthermore, the proposed embedded solution can be deployed on the unmanned ground vehicles to detect, count, and measure the size of the apples in real-time to help the farmers and agronomists in their decision making and management skills.
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
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 source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The technology is rapidly evolving, with new techniques and frameworks being developed to improve the performance, efficiency, and security of Edge AI solutions [62].”
From Edge AI: A survey (2023) · cites this paper as [62]
Experimental — accuracy not yet measured
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
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 1×
“Darknet-19 is a light and efficient feature extractor, but can be easily swapped with any other backbone like ResNet [40], DenseNet [41], etc.”
BackgroundVery Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148 · cited 2×
“Faster R-CNN with VGG16 net [18] is the state-of-art method in fruit detection [10].”
MethodFaster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472 · cited 5×
“However, Faster R-CNN consists of region proposal networks (RPN) and clas-sification networks that produced excellent results in terms of accuracy, while the detection speed is slow, which can not achieve good results in real-time with high image resolution.”
MethodInfluentialFaster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1506.01497 · Cited by 70,812 · cited 5×
“However, Faster R-CNN consists of region proposal networks (RPN) and clas-sification networks that produced excellent results in terms of accuracy, while the detection speed is slow, which can not achieve good results in real-time with high image resolution.”
MethodInfluentialImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333 · cited 1×
“That is not true with larger data set like ImageNet [48], where labels are arranged as a directed graph [49] and not as flat structure.”
BackgroundYou Only Look Once: Unified, Real-Time Object Detection
Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.91 · Cited by 53,803 · cited 3×
“The You Only Look Once (YOLO) method [19], [20] deals with the classification and the localization as a regression problem.”
BackgroundMethodDensely Connected Convolutional Networks
Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.243 · Cited by 48,566
Microsoft COCO: Common Objects in Context
Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., & Zitnick, C. L. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10602-1_48 · Cited by 45,460
Feature Pyramid Networks for Object Detection
Lin, T.-Y., Dollar, P., Girshick, R., He, K., Hariharan, B., & Belongie, S. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.106 · Cited by 30,939 · cited 1×
“That is achieved with 1x1 convolutions arranged in a Pyramid Network [44] structure.”
MethodFocal Loss for Dense Object Detection
Lin, T.-Y., Goyal, P., Girshick, R., He, K., & Dollar, P. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.324 · Cited by 30,581 · cited 1×
“It has comparable performance in terms of accuracy with other popular object detection algorithms like RetinaNet [37], Faster-RCNN [38], but it is much faster and compact that makes it an optimal choice for real-time embedded applications.”
Method
Research works printed but not linked: 6
- 2019, Graphics Reinvented NVIDIA GeForce RTX 2080 Ti Graphics Card
- 2019, NVIDIA Jetson—Hardware For Every Situation
- 2019, Intel Neural Compute Stick
- 2019, Intel movidius neural compute stick
- rosebrock, 2017, Deep Learning for Computer Vision with Python Starter Bundle
- silwal, 2016, Apple identification in field environment with over the row machine vision system, Agricultural Engineering International the CIGRE Journal, 16, 66
Cited by
Singh, R., & Gill, S. S. (2023) · Internet of Things and Cyber-Physical Systems · doi:10.1016/j.iotcps.2023.02.004 · Cited by 572
Wu, D., Lv, S., Jiang, M., & Song, H. (2020) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2020.105742 · Cited by 496
A Survey of Recent Advances in Edge-Computing-Powered Artificial Intelligence of Things
Chang, Z., Liu, S., Xiong, X., Cai, Z., & Tu, G. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3088875 · Cited by 418
Efficient-CapsNet: capsule network with self-attention routing
Mazzia, V., Salvetti, F., & Chiaberge, M. (2021) · Scientific Reports · doi:10.1038/s41598-021-93977-0 · Cited by 240
Self-citationChen, C.-J., Huang, Y.-Y., Li, Y.-S., Chen, Y.-C., Chang, C.-Y., & Huang, Y.-M. (2021) · IEEE Access · doi:10.1109/access.2021.3056082 · Cited by 192
Real-time growth stage detection model for high degree of occultation using DenseNet-fused YOLOv4
Roy, A. M., & Bhaduri, J. (2022) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2022.106694 · Cited by 177
A Real-Time Apple Targets Detection Method for Picking Robot Based on ShufflenetV2-YOLOX
Ji, W., Pan, Y., Xu, B., & Wang, J. (2022) · Agriculture · doi:10.3390/agriculture12060856 · Cited by 160
Zhang, Y.-C. S. L.-G., Yu, J., Chen, Y., Yang, W. T., Zhang, W., & He, Y. (2021) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2021.106586 · Cited by 150
Towards autonomous mapping in agriculture: A review of supportive technologies for ground robotics
Fasiolo, D. T., Scalera, L., Maset, E., & Gasparetto, A. (2023) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2023.104514 · Cited by 140
Detection, classification, and mapping of coffee fruits during harvest with computer vision
Bazame, H. C., Molin, J. P., Althoff, D., & Martello, M. (2021) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2021.106066 · Cited by 107
Vision systems for harvesting robots: Produce detection and localization
Montoya-Cavero, L.-E., Torres, R. D. D. L., Gómez-Espinosa, A., & Cabello, J. A. E. (2021) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2021.106562 · Cited by 119
Artificial Intelligence in the IoT Era: A Review of Edge AI Hardware and Software
Sipola, T., Alatalo, J., Kokkonen, T., & Rantonen, M. (2022) · 2022 31st Conference of Open Innovations Association (FRUCT) · doi:10.23919/fruct54823.2022.9770931 · Cited by 100
“Application for tangible real-world problem solving is the An Edge AI based apple detection solution has been created to count apples and estimate their sizes [31].”
BackgroundA comprehensive review on applications of Raspberry Pi
Mathe, S. E., Kondaveeti, H. K., Vappangi, S., Vanambathina, S. D., & Kumaravelu, N. K. (2024) · Computer Science Review · doi:10.1016/j.cosrev.2024.100636 · Cited by 144
Advances in apple’s automated orchard equipment: A comprehensive research
Mhamed, M., Zhang, Z., Yu, J., Li, Y., & Zhang, M. (2024) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2024.108926 · Cited by 96
Smart Agriculture: Current State, Opportunities, and Challenges
Ahmed, B., Shabbir, H., Naqvi, S. R., & Peng, L. (2024) · IEEE Access · doi:10.1109/access.2024.3471647 · Cited by 122
“The precision farming techniques can help reduce environmental effects, but their adoption varies [141].”
BackgroundDeep Learning Framework for Vehicle and Pedestrian Detection in Rural Roads on an Embedded GPU
Barba-Guaman, L., Eugenio Naranjo, J., & Ortiz, A. (2020) · Electronics · doi:10.3390/electronics9040589 · Cited by 82
Aghi, D., Mazzia, V., & Chiaberge, M. (2020) · Machines · doi:10.3390/machines8020027 · Cited by 90
“affeNet [38] to detect diseases in plants and leaves respectively. Moreover, deep learning has been used for crop type classification [39,40,41,42], crop yield estimation [43,44,45,46], fruit counting [24,47,48], and even to predict the weather, forecasting temperature and rainfall[49]. We propose a novel approach base…”
MethodSelf-citationApple Detection in Complex Scene Using the Improved YOLOv4 Model
Wu, L., Ma, J., Zhao, Y., & Liu, H. (2021) · Agronomy · doi:10.3390/agronomy11030476 · Cited by 83
“Therefore, to simulate this scene, we randomly multiply the original image with a scaling factor between 0.5 and 1.5.”
MethodInfluentialZualkernan, I. A., Abuhani, D. A., Hussain, M. H., Khan, J., & ElMohandes, M. (2023) · Drones · doi:10.3390/drones7060382 · Cited by 100
“…architectures, by compressing a dense model, by using an effective model with a small number of parameters, or by using a hardware accelerator that can be deployed on an embedded system-on-chip (SoC) that includes graphic processing units (GPUs) or field-programmable gate arrays (FPGAs) [136].”
MethodAn architecture-level analysis on deep learning models for low-impact computations
Li, H., Wang, Z., Yue, X., Wang, W., Tomiyama, H., & Meng, L. (2022) · Artificial Intelligence Review · doi:10.1007/s10462-022-10221-5 · Cited by 77
“For embedded systems, such as mobile devices and robotics, the hardware resources are quite constrained while the application efficiency is highly demanded (Mazzia et al. 2020).”
BackgroundModel-driven Cluster Resource Management for AI Workloads in Edge Clouds
Liang, Q., Hanafy, W. A., Ali-Eldin, A., & Shenoy, P. J. (2023) · ACM Transactions on Autonomous and Adaptive Systems · doi:10.1145/3582080 · Cited by 71
Simultaneous fruit detection and size estimation using multitask deep neural networks
Ferrer-Ferrer, M., Ruiz‐Hidalgo, J., Gregorio, E., Vilaplana, V., Morros, J. R., & Gené-Mola, J. (2023) · Biosystems Engineering · doi:10.1016/j.biosystemseng.2023.07.010 · Cited by 67
“Furthermore, since it is based on a CNN that can be processed with graphic processing units (GPUs) and parallel computing, our method will permit its use for real-time and edge-computing applications (Mazzia et al., 2020).”
MethodLow-Cost CNN for Automatic Violence Recognition on Embedded System
Vieira, J. C., Sartori, A., Stefenon, S. F., Perez, F. L., de Jesus, G. S., & Leithardt, V. R. Q. (2022) · IEEE Access · doi:10.1109/access.2022.3155123 · Cited by 65
“Although typically the training phase requires more processing power than running the model [29], computationally limited systems such as small computers and embedded systems still face major difficulties in reproducing such models efficiently [30].”
BackgroundAkdoğan, C., Özer, T., & Oğuz, Y. (2025) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2025.110052 · Cited by 63
Real-time fruit detection using deep neural networks on CPU (RTFD): An edge AI application
Mao, D., Sun, H., Li, X., Yu, X., Wu, J., & Zhang, Q. (2022) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2022.107517 · Cited by 64
Evaluation Method of Deep Learning-Based Embedded Systems for Traffic Sign Detection
Lopez-Montiel, M. A., Orozco-Rosas, U., Sánchez-Adame, M., Picos, K., & Montiel, O. (2021) · IEEE Access · doi:10.1109/access.2021.3097969 · Cited by 61
“Several works [58]–[60] consider Memory consumption , Energy consumption , Latency , and Throughput as the most relevant metrics for DL implementation; thus, these metrics are evaluated in this methodology.”
BackgroundPosition-Agnostic Autonomous Navigation in Vineyards with Deep Reinforcement Learning
Martini, M., Cerrato, S., Salvetti, F., Angarano, S., & Chiaberge, M. (2022) · IEEE International Conference on Automation Science and Engineering (CASE) · doi:10.1109/case49997.2022.9926582 · Cited by 52
“Deep Learning (DL) methods are more and more used in the context of precision agriculture [19], [20] to tackle many different tasks such as object detection [21], [22], fruit”
MethodSelf-citationDetecting volunteer cotton plants in a corn field with deep learning on UAV remote-sensing imagery
Yadav, P. K., Thomasson, J. A., Hardin, R. G., Searcy, S. W., Braga-Neto, U., Popescu, S., Martin, D. E., Rodríguez, R. M., Meza, K., Enciso, J., et al. (2022) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2022.107551 · Cited by 57
Edge AI: A Comprehensive Survey of Technologies, Applications, and Challenges
Shankar, V. (2024) · International Conference on Advanced Computing and Emerging Technologies (ACET) · doi:10.1109/acet61898.2024.10730112 · Cited by 74
“Vittorio and colleagues [8] propose a real-time embedded solution for apple recognition using the YOLOv3-tiny algorithm, and have successfully implemented it across multiple platforms.”
MethodJi, W., Zhai, K., Xu, B., & Wu, J. (2024) · Journal of Food Protection · doi:10.1016/j.jfp.2024.100397 · Cited by 53
Face Detection and Recognition, Face Emotion Recognition Through NVIDIA Jetson Nano
Sati, V., Márquez-Sánchez, S., Shoeibi, N., Arora, A., & Corchado, J. M. (2020) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-58356-9_18 · Cited by 56
Ag-YOLO: A Real-Time Low-Cost Detector for Precise Spraying With Case Study of Palms
Qin, Z., Wang, W., Dammer, K.-H., Guo, L., & Cao, Z. (2021) · Frontiers in Plant Science · doi:10.3389/fpls.2021.753603 · Cited by 41
“It is unnecessary to use more predictors for a light model (e.g., in Mazzia et al., 2020) if the backbone network has enough representational power, which is because that more predictors bring more computation complexity.”
MethodAn improved Tiny YOLOv3 for real-time object detection
Gai, W., Liu, Y., Zhang, J., & Jing, G. (2021) · Systems Science & Control Engineering · doi:10.1080/21642583.2021.1901156 · Cited by 44
Forecasting Air Temperature on Edge Devices with Embedded AI
Codeluppi, G., Davoli, L., & Ferrari, G. (2021) · Sensors · doi:10.3390/s21123973 · Cited by 42
“3 (namely, ANN((10)) 5 ) can be deployed on a real IoT edge device, denoted as Smart GW, such as a Raspberry Pi (RPi) [33], which represents a popular Single Board Computer (SBC) in EdgeAI applications [34,35].”
MethodEdge artificial intelligence for big data: a systematic review
Hemmati, A., Raoufi, P., & Rahmani, A. M. (2024) · Neural Computing and Applications · doi:10.1007/s00521-024-09723-w · Cited by 51
“…proposed model successfully undermines the classifiers Optimize for diverse poisoning attack scenarios; Address potential classifier vulnerabilities Mazzia et al. [72] proposed a real-time embedded solution for apple detection in orchards using the YOLOv3-tiny algorithm on various embedded platforms.”
Maski, P., & Thondiyath, A. (2021) · 2021 6th International Conference on Image, Vision and Computing (ICIVC) · doi:10.1109/icivc52351.2021.9526944 · Cited by 34
Design of Citrus Fruit Detection System Based on Mobile Platform and Edge Computer Device
Huang, H., Huang, T., Li, Z., Lyu, S., & Hong, T. (2021) · Sensors · doi:10.3390/s22010059 · Cited by 39
“[24] implemented the YOLOv3-Tiny target detection algorithm on different embedded platforms.”
MethodDouklias, A., Karagiannidis, L., Misichroni, F. D., & Amditis, A. (2022) · Sensors · doi:10.3390/s22052049 · Cited by 38
“Many researchers have performed benchmarking of the performance of various embedded devices that can be hosted by a UAV either explicitly [33–37] or implicitly [18,38,39] as part of their work.”
BackgroundYu, Z., Ye, J., Li, C., Zhou, H., & Li, X. (2023) · Frontiers in Plant Science · doi:10.3389/fpls.2023.1158940 · Cited by 44
Kreković, D., Krivić, P., Žarko, I. P., Kušek, M., & Le-Phuoc, D. (2025) · Internet of Things · doi:10.1016/j.iot.2025.101553 · Cited by 57
Trends for Low-Cost and Open-Source IoT Solutions Development for Industry 4.0
Martikkala, A., David, J., Lobov, A., Lanz, M., & Ituarte, I. F. (2021) · Procedia Manufacturing · doi:10.1016/j.promfg.2021.10.042 · Cited by 48
Yang, Y.-K. (2024) · Measurement Sensors · doi:10.1016/j.measen.2024.101086 · Cited by 30
DeepWay: A Deep Learning waypoint estimator for global path generation
Mazzia, V., Salvetti, F., Aghi, D., & Chiaberge, M. (2021) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2021.106091 · Cited by 35
Self-citationA Deep Learning Driven Algorithmic Pipeline for Autonomous Navigation in Row-Based Crops
Cerrato, S., Mazzia, V., Salvetti, F., Martini, M., Angarano, S., Navone, A., & Chiaberge, M. (2024) · IEEE Access · doi:10.1109/access.2024.3465873 · Cited by 42
“That effectively scales down computational requirements enabling low-power computational devices boosted by hardware accelerators such as visual processing units (VPUs), tensor processing units (TPUs), and embedded GP-GPUs, [21].”
BackgroundSelf-citationLohakan, M., & Seetao, C. (2024) · Heliyon · doi:10.1016/j.heliyon.2024.e31366 · Cited by 43
“The results demonstrate significant potential for real-time power consumption monitoring [16].”
BackgroundZhang, Y., He, S., Wa, S., Zong, Z., & Liu, Y. (2021) · Information · doi:10.3390/info12120495 · Cited by 30
Image classification on smart agriculture platforms: Systematic literature review
Restrepo-Arias, J. F., Branch, J. W., & Awad, G. (2024) · Artificial Intelligence in Agriculture · doi:10.1016/j.aiia.2024.06.002 · Cited by 48
Mahmud, M. S., Zahid, A., & Das, A. K. (2023) · Sensors · doi:10.3390/s23041818 · Cited by 45
LR-Net: A Block-based Convolutional Neural Network for Low-Resolution Image Classification
Ganj, A., Ebadpour, M., Darvish, M., & Bahador, H. J. (2023) · Iranian Journal of Science and Technology Transactions of Electrical Engineering · doi:10.1007/s40998-023-00618-5 · Cited by 27
“Deep convolutional neural networks (CNNs) have revolutionized computer vision in recent years, and are widely used in various tasks such as object detection [1, 2], image classification [3, 4], and instance image segmentation [2].”
MethodDevelopments in Automated Harvesting Equipment for the Apple in the orchard: Review
Tianjing, Y., & Mhamed, M. (2024) · Smart Agricultural Technology · doi:10.1016/j.atech.2024.100491 · Cited by 30
YOLOv9s-Pear: A Lightweight YOLOv9s-Based Improved Model for Young Red Pear Small-Target Recognition
Shi, Y., Duan, Z., Qing, S., Zhao, L. F., Wang, F., & Yuwen, X. (2024) · Agronomy · doi:10.3390/agronomy14092086 · Cited by 28
Stasenko, N., Shukhratov, I., Savinov, M., Shadrin, D., & Somov, A. (2023) · Entropy · doi:10.3390/e25070987 · Cited by 28
Zhou, L., Zhang, C., Taha, M. F., Qiu, Z., & He, Y. (2021) · Transactions of the ASABE · doi:10.13031/trans.13989 · Cited by 25
Chen, J., Li, S., Yang, K., Wei, C., & Tang, X. (2023) · IEEE Transactions on Transportation Electrification · doi:10.1109/tte.2023.3288364 · Cited by 24
“Finally, during the PIL, the strategies fit by networks are directly loaded into the edge devices, NVIDIA Jetson Nano and NVIDIA Jetson AGX Xavier [39], and the updating of the control strategies is prohibited, resulting in PIL tests being tested with a deterministic strategy, which aims at…”
MethodTyacke, E., Reddy, S. P. J., Feng, N., Edlabadkar, R., Zhou, S., Patel, J., Hu, Q., & Atashzar, S. F. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3191238 · Cited by 26
Precision agriculture and the digital contributions for site-specific management of the fields
Molin, J. P., Bazame, H. C., Maldaner, L. F., Corrêdo, L. D. P., Martello, M., & Canata, T. F. (2020) · Ciência Agronômica/Revista ciência agronômica · doi:10.5935/1806-6690.20200088 · Cited by 39
“…and harvesting of fruits using agricultural robots (XIONG et al., 2020), identification and classification of plants (BAO et al., 2019; GRINBLAT et al., 2016; LIU et al., 2020; MAZZIA et al., 2020; TU et al., 2020 AI has provided farmers and technicians solutions to many crop-related issues.”
BackgroundDang, C., Wang, Z., He, Y., Wang, L., Cai, Y., Shi, H., & Jiang, J. (2023) · IEEE Access · doi:10.1109/access.2023.3334973 · Cited by 22
“This poses challenges like substantial network latency and heightened energy and financial implications [16].”
BackgroundEnhancing visual autonomous navigation in row-based crops with effective synthetic data generation
Martini, M., Ambrosio, M., Navone, A., Tuberga, B., & Chiaberge, M. (2024) · Precision Agriculture · doi:10.1007/s11119-024-10157-6 · Cited by 25
“…solutions for different tasks such as harvesting (Droukas et al., 2023), spraying (Deshmukh et al., 2021), yield estimation (Maheswari et al., 2021; Mazzia et al., 2020), disease detection (Ferentinos, 2018; Shruthi et al., 2019) and crop detection and monitoring (Comba et al., 2019; Vidović et…”
Self-citationLightweight Algorithm for Apple Detection Based on an Improved YOLOv5 Model
Sun, Y., Zhang, D., Guo, X., & Yang, H. M. (2023) · Plants · doi:10.3390/plants12173032 · Cited by 22
“[37] employed a YOLOv3-tiny algorithm on embedded platforms such as Raspberry Pi 3 B+ with Intel Movidius Neural Computing Stick (NCS), Nvidia’s Jetson Nano, and Jetson AGX Xavier.”
MethodLu, X., Suganuma, M., & Okatani, T. (2024) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv57701.2024.00116 · Cited by 47
“Nonetheless, these processors have been utilized in various real-world applications such as smart agriculture [41, 69] and AI applications for fishery [60] and livestock management [2,30], where limited computational resources are sufficient.”
BackgroundGPS-free autonomous navigation in cluttered tree rows with deep semantic segmentation
Navone, A., Martini, M., Ambrosio, M., Ostuni, A., Angarano, S., & Chiaberge, M. (2024) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2024.104854 · Cited by 20
Self-citationImplementation of a Compact Traffic Signs Recognition System Using a New Squeezed YOLO
Khnissi, K., Jabeur, C. B., & Seddik, H. (2022) · International Journal of Intelligent Transportation Systems Research · doi:10.1007/s13177-022-00304-6 · Cited by 19
Partition harvesting of a column-comb litchi harvester based on 3D clustering
Li, C., Lin, J., Li, B., Zhang, S., & Li, J. (2022) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2022.106975 · Cited by 19
Smart Count System Based on Object Detection Using Deep Learning
Moon, J.-W., Lim, S., Lee, H., Yu, S., & Lee, K.-B. (2022) · Remote Sensing · doi:10.3390/rs14153761 · Cited by 22
Real-time biodiversity analysis using deep-learning algorithms on mobile robotic platforms
Panigrahi, S., Maski, P., & Thondiyath, A. (2023) · PeerJ Computer Science · doi:10.7717/peerj-cs.1502 · Cited by 20
“8, while other functional specifications are extracted from the existing literature ( Mazzia et al., 2020 ; Meng et al., 2020 ).”
Location and timestamp-based chip contour detection using LWMG-YOLOv5
Chang, B. R., Tsai, H. F., & Hsieh, C.-W. (2023) · Computers & Industrial Engineering · doi:10.1016/j.cie.2023.109277 · Cited by 18
Boschi, A., Salvetti, F., Mazzia, V., & Chiaberge, M. (2020) · Machines · doi:10.3390/machines8030049 · Cited by 18
“cessing Unit (TPU) chips. In the literature can be found several works which apply optimization techniques to object detection algorithms to deploy them on embedded devices with hardware acceleration [48,49,50,51,52]. In our work, we fine-tuned a pre-trained YOLOv3-tiny network for the person detection task, and we pro…”
BackgroundSelf-citationLee, S., Kim, H., Jeong, B., & Yoon, J. (2021) · Applied Sciences · doi:10.3390/app11020643 · Cited by 18
“Now that many efficient and compressed CNN architectures have been proposed, many researchers and major IT companies are focusing on how to shift these compression models to edge devices as customers spend more time on mobile devices [38–41 , 44– 48].”
BackgroundSmart metering system data analytics platform using multicore edge computing
Olivares-Rojas, J. C., Reyes‐Archundia, E., Gnecchi, J. A. G., Molina‐Moreno, I., Téllez-Anguiano, A. C., & Jacobo, J. C. (2021) · International Journal of Reconfigurable and Embedded Systems (IJRES) · doi:10.11591/ijres.v10.i1.pp11-17 · Cited by 15
“The use of SBC with the integration of GPU use has been studied by various works [13-15] in which the Jetson Nano board stands out for its excellent performance and low costs.”
MethodRuparelia, S., Jethva, M., & Gajjar, R. (2021) · Advances in intelligent systems and computing · doi:10.1007/978-981-16-2123-9_39 · Cited by 16
Online sorting of drilled lotus seeds using deep learning
Lu, A., Guo, R., Ma, Q., Ma, L., Cao, Y., & Liu, J. (2022) · Biosystems Engineering · doi:10.1016/j.biosystemseng.2022.06.015 · Cited by 19
Lightweight deep learning for tomato disease detection: trends, challenges, and edge AI perspectives
Gunasekaran, H., Rajkumar, S., & Benjamin, L. K. (2026) · Frontiers in Plant Science · doi:10.3389/fpls.2025.1737208 · Cited by 22
“…occur in local devices with the following advantages: (cid:129) Low latency: Predictions are generated within milliseconds, supporting timely decision-making in fi eld conditions (Mazzia et al., 2020 (cid:129) Cost ef fi ciency: Removes reliance on expensive cloud servers or network infrastructure.”
22. Grape yield spatial variability assessment using YOLOv4 object detection algorithm
Sozzi, M., Cantalamessa, S., Cogato, A., Kayad, A. G., & Marinello, F. (2021) · Wageningen Academic Publishers eBooks · doi:10.3920/978-90-8686-916-9_22 · Cited by 15
Waypoint Generation in Row-Based Crops with Deep Learning and Contrastive Clustering
Salvetti, F., Angarano, S., Martini, M., Cerrato, S., & Chiaberge, M. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-26422-1_13 · Cited by 15
“agricultural tasks such as fruit detection and counting [23], plant disease identification [11, 25], land coverage and vegetation index classification from satellite and Unmanned Aerial Vehicles (UAVs) imagery [15,21,22].”
BackgroundSelf-citationAn Integer-Only Resource-Minimized RNN on FPGA for Low-Frequency Sensors in Edge-AI
Bartels, J., Hagihara, A., Minati, L., Tokgöz, K. K., & Ito, H. (2023) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3286580 · Cited by 18
“Furthermore, Edge-AI offers benefits when deployed near end-users, as it enables processing and transmission of class labels in real time [11].”
BackgroundHierarchical Modified Fast R-CNN for Object Detection
Chaudhuri, A. (2021) · Informatica · doi:10.31449/inf.v45i7.3732 · Cited by 22
Moniruzzaman, M., Okilly, A. H., Choi, S., Baek, J., Mannan, T. I., & Islam, Z. (2024) · Conference proceedings/Conference proceedings - IEEE Applied Power Electronics Conference and Exposition · doi:10.1109/apec48139.2024.10509167 · Cited by 20
Maltezos, E., Douklias, A., Dadoukis, A., Misichroni, F. D., Karagiannidis, L., Αντωνόπουλος, Μ., Voulgary, K., Ouzounoglou, E., & Amditis, A. (2021) · Computation · doi:10.3390/computation9020012 · Cited by 15
“To meet these needs the Jetson AGX Xavier is installed on board the UAV, and is assumed to be a powerful unit achieving better performance compared to other units [29,30].”
BackgroundRemote Crop Sensing with IoT and AI on the Edge
Savvidis, P., & Papakostas, G. A. (2021) · IEEE World AI IoT Congress (AIIoT) · doi:10.1109/aiiot52608.2021.9454237 · Cited by 14
“A relevant research using various SBCs platforms had been published by Mazzia et al. [5], which is the most relevant work to our research as they used similar equipment, framework and a subject of recognition.”
MethodAccelerated Computer Vision Inference with AI on the Edge
Mittal, V., & Bhushan, B. (2020) · IEEE International Conference on Communication Systems and Network Technologies (CSNT) · doi:10.1109/csnt48778.2020.9115770 · Cited by 19
“This is the essence of AI on the Edge [16].”
BackgroundAmogi, B. R., Ranjan, R., & Khot, L. R. (2023) · Information Processing in Agriculture · doi:10.1016/j.inpa.2023.12.001 · Cited by 21
An NB-IoT-Based Edge-of-Things Framework for Energy-Efficient Image Transfer
Khan, S. Z., Moullec, Y. L., & Alam, M. M. (2021) · Sensors · doi:10.3390/s21175929 · Cited by 12
“In general, there could be a number of use-cases where image transmission would be required by applications such as [16,51,52], etc.”
BackgroundCotton Stubble Detection Based on Improved YOLOv3
Yang, Y., Li, J., Nie, J., Yang, S., & Tang, J. (2023) · Agronomy · doi:10.3390/agronomy13051271 · Cited by 13
Márquez-Sánchez, S., Lecumberri, F., Sati, V., Arora, A., Shoeibi, N., Rodríguez, S., & Rodríguez‐Díaz, J. M. (2020) · Communications in computer and information science · doi:10.1007/978-3-030-51999-5_32 · Cited by 22
Developments of the Automated Equipment of Apple in the Orchard: A Comprehensive Review
Mhamed, M., Kabir, M. H., & Zhang, Z. (2023) · Smart agriculture · doi:10.1007/978-981-99-6124-5_1 · Cited by 10
Vehicle identification and analysis based on lightweight YOLOv5 on edge computing platform
Hong, T., Ma, Y., & Jiang, H. (2024) · Measurement Science and Technology · doi:10.1088/1361-6501/ad9bd4 · Cited by 10
“To address these limitations, edge computing (often referred to as ‘edge artificial intelligence’) is introduced, enabling the acquisition and local execution of data from various devices or sensors [20].”
Augmentation Method for High Intra-Class Variation Data in Apple Detection
Li, H., Guo, W., Lu, G., & Shi, Y. (2022) · Sensors · doi:10.3390/s22176325 · Cited by 10
Embedded Real-Time Clothing Classifier Using One-Stage Methods for Saving Energy in Thermostats
Medina, A., Méndez, J. I., Ponce, P., Peffer, T. E., & Molina, A. (2022) · Energies · doi:10.3390/en15176117 · Cited by 11
Machine vision system for real-time debris detection on mechanical wild blueberry harvesters
Das, A. K., Esau, T. J., Zaman, Q. U., Farooque, A. A., Schumann, A. W., & Hennessy, P. J. (2022) · Smart Agricultural Technology · doi:10.1016/j.atech.2022.100166 · Cited by 13
Real-Time Automated Classification of Sky Conditions Using Deep Learning and Edge Computing
Czarnecki, J. M. P., Samiappan, S., Zhou, M., McCraine, C. D., & Wasson, L. (2021) · Remote Sensing · doi:10.3390/rs13193859 · Cited by 10
Rodríguez, I., Campos, C., & Fdez‐Riverola, F. (2021) · Applied Sciences · doi:10.3390/app11199173 · Cited by 13
“The majority of those datasets are image sets created from scratch, either by actively taking pictures in real-world scenes [50,77,80,84,86,91,98,100,103,109] or by extracting frames from previously recorded videos [64,95] but there are also three exceptions that reuse images already present in other existing datasets…”
BackgroundInfluentialDeployment of Embedded Edge-AI for Wildlife Monitoring in Remote Regions
Schwartz, D., Gomes-Selman, J. M., Wrege, P. H., & Paepcke, A. (2021) · International Conference on Machine Learning and Applications · doi:10.1109/icmla52953.2021.00170 · Cited by 14
“For example, [14] introduces a model for estimating the number and weight of apples in an orchard.”
BackgroundCitrus yield estimation for individual trees integrating pruning intensity and image views
Zhu, Y., Liu, F., Zhao, Y., Gu, Q., & Zhang, X. (2024) · European Journal of Agronomy · doi:10.1016/j.eja.2024.127349 · Cited by 9
Real-Time Drone Anti-Collision Avoidance Systems: an Edge Artificial Intelligence Application
Lahsen-Cherif, I., Liu, H., & Lamy–Bergot, C. (2022) · IEEE Radar Conference (RadarConf) · doi:10.1109/radarconf2248738.2022.9764175 · Cited by 9
“The authors of [9] propose an implementation of a tiny version of the YOLO model for a real-time object detection application.”
MethodFast and Accurate Deep Learning Model for Stamps Detection for Embedded Devices
Gayer, A. V., Ershova, D. M., & Arlazarov, V. V. (2022) · Pattern Recognition and Image Analysis · doi:10.1134/s1054661822040046 · Cited by 9
“A particularly important fact is that the authors conducted experiments with a simplified version of the network called Tiny YOLO v3 [17], but they failed to achieve acceptable quality and they do not present the results of experiments with this architecture.”
BackgroundFarzadmehr, M., Carlan, V., & Vanelslander, T. (2024) · WMU Journal of Maritime Affairs · doi:10.1007/s13437-024-00334-9 · Cited by 15
Apple Trees Diseases Detection Through Computer Vision in Embedded Systems
Logashov, D., Shadrin, D., Somov, A., Pukalchik, M., Uryasheva, A., Gupta, H. P., & Rodichenko, N. (2021) · IEEE International Symposium on Industrial Electronics (ISIE) · doi:10.1109/isie45552.2021.9576438 · Cited by 9
“These problems can be addressed by using the automatic monitoring systems equipped with the optoelectronic devices [7] and Deep Learning (DL) algorithms for image processing running on-board of the embedded systems [8] [9].”
BackgroundDDR-YOLO: An Efficient Detection Model Based on YOLO11s for Steel Surface Defect
Ren, X., Liu, Z., Cheng, H., & Chen, L. (2025) · IEEE Access · doi:10.1109/access.2025.3599978 · Cited by 12
“In addition, YOLO series detection algorithms such as YOLOv3-tiny [59], YOLOv5s [7], YOLOv6s [25], YOLOv8s [10], YOLOv9s [42], YOLOv10s [43], YOLO11s [34], YOLOv12s [44], and YOLO13s [45] are selected as comparison algorithms.”
Object Detection Using ESRGAN With a Sequential Transfer Learning on Remote Sensing Embedded Systems
Musunuri, Y. R., Kim, C., Kwon, O., & Kung, S. (2024) · IEEE Access · doi:10.1109/access.2024.3432532 · Cited by 17
“TL is a powerful technique widely utilized in remote sensing and edge computing applications [50], [51], [52], [53] to enhance embedded image processing performance.”
MethodDeep Learning-Based Detection of Articulatory Features in Arabic and English Speech
Algabri, M., Mathkour, H. I., Alsulaiman, M. M., & Bencherif, M. A. (2021) · Sensors · doi:10.3390/s21041205 · Cited by 9
Metadata
- Authors
- Mazzia, V., Khaliq, A., Salvetti, F., & Chiaberge, M.
- Affiliations
- Politecnico di Torino (IT)
- Venue
- IEEE Access
- Published
- 2020
- Volume
- 8
- Pages
- 9102-9114
- ISSN
- 2169-3536 (ISSN-L)
- OpenAlex
- W3000086329
- Cited by
- 212
- References
- 59
- Citations by year
- 2026: 21 · 2025: 18 · 2024: 36 · 2023: 42 · 2022: 40 · 2021: 42 · 2020: 13
- FWCI
- 22.13
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- IEEE Access (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- PORTO@Iris (submittedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- arXiv (Cornell University) (cc-by)
- Funders
- Politecnico di Torino
- Topics
- Life Sciences › Agricultural and Biological Sciences › Plant Science › Smart Agriculture and AI
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
- Keywords
- apple detection, real-time object detection, edge AI, embedded systems, YOLOv3-tiny, hardware accelerators, Jetson Nano, NVIDIA Jetson AGX Xavier, Raspberry Pi, unmanned ground vehicles, small object detection, orchard monitoring
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.