Novel real-time safety algorithm for predicting multi-targets in the farmland road

Xiaoming Liang, Fu'en Chen, Longhan Chen, Deyue Li, Bin Guo, Yubo Liang, Yubin Lan

Abstract


The more information obtained about the driving environment, the more ensures driving safety. Due to the complex driving environment of farmland roads, targets beside the road sometimes have an important impact on driving safety. To achieve this goal, a novel real-time detection and prediction algorithm of targets was proposed. The whole image was divided into four parts by RCM: driving region, crossroad region, roadside region, and the other region. In addition, a safety policy for every part was enforced by the algorithm, which was based mainly on the combination of the YOLACT and GPM. On this basis, a self-collected data set of 5000 test samples is used for testing. The detection accuracy of the algorithm in the data set could reach up to 90%, and the processing speed to 30.4 fps. In addition, experiments were carried out on actual farmland roads, and the results showed that the proposed algorithm was able to detect, track, and predict targets on the farmland road, and alarm to driver in time before the targets rush into the road. This study provides an important reference for the safe driving of agricultural vehicles.
Keywords: real-time, safety, algorithm for predicting, multi-target, farmland road, computer vision
DOI: 10.25165/j.ijabe.20231606.7876

Citation: Liang X M, Chen F, Chen L H, Li D Y, Guo B, Liang Y B, et al. Novel real-time safety algorithm for predicting
multi-target in the farmland road. Int J Agric & Biol Eng, 2023; 16(5): 198–207.

Keywords


real-time, safety, algorithm for predicting, multi-target, farmland road, computer vision

Full Text:

PDF

References


National Bureau of Statistics of China. Statistical bulletin of national economic and social development of the People’s Republic of China in 2019. Available:http://www.stats.gov.cn/tjsj/zxfb/202002/t20200228_1728913.html. (in Chinese)

Xu X, Analysis of Road Traffic Accidents in China and Measures to Prevent Them. China Safety Science Journal, 2013; 23(11): 120–125 (in Chinese).

Yang L L, Xu Y Y, Liang Y J, Qin J, Li Y B, Wang X X, et al. Extractionof Straight Field Roads between Farmlands based on Agricultural Vehiclemounted LiDAR. Int J Agric & Biol Eng, 2022; 15(5): 155–162.

Guo J B, Wang G Q, Guan W, Chen Z R, Liu Z B. A Feasible Region Detection Method for Vehicles in Unstructured Environments based on PSMNet and Improved RANSAC. Multimed Tools Appl, 2023; 82: 43967–43989.

Vivek K P, Akash C G, Ayesha C and Ayesha C. Computer Vision and Deep Learning Based Framework for Road Scene and Surface Segmentation in Unstructured Environment. 2022 IEEE International Conference on Service Operations and Logistics, and Informatics (SOLI), Delhi, India, 2022; pp.1–6. doi: 10.1109/SOLI57430.2022.10294507.

Lei G N, Yao R T, Zhao Y D, Zheng Y L. Detection and Modeling of Unstructured Roads in Forest Areas Based on Visual-2D Lidar Data Fusion. Forests, 2021; 12(7): 820.

Zhu M Y, Wang H P, Li P P, Liu J T. An ANN-based Unstructured Road Detection Approach under Time-varying Illumination. 2019 IEEE International Conference on Real-time Computing and Robotics, Kandima, Maldives, 2019; pp.293–298. doi: 10.1109/RCAR47638.2019.9044119

Chen W W, Wang W X, Wang K, Li Z Y, Li H, Liu S. Lane Departure Warning Systems and Lane Line Detection Methods based on Image Processing and Semantic Segmentation: A Review. Journal of Traffic and Transportation Engineering (English Edition), 2020; 7(6): 748–774.

Li J B, Chen B Q, Liu Y, Zha T. Detection for Navigation Route for Cotton Harvester based on Machine Vision. Transactions of the CSAE, 2013; 29(11): 11–19 (in Chinese).

Liu Z G, Du J, Tian F, Wen J Z. Traffic Sign Recognition Using an Attentive Context Region-Based Detection Framework. Chinese Journal of Electronics, 2021; 30(6): 1080–1086.

Choi K H, Han S K, Han S H, Park K H, Kim K S, Kim S. Morphologybased Guidance Line Extraction for An Autonomous Weeding Robot in Paddy Fields. Computers and Electronics in Agriculture, 2015; 113:

–274.

Wang X W, Li S H, Liang X, Zheng J J. Drivable Region Recommendation Model for Unstructured Road Based on M-shaped Deep Architecture. China Journal of Highway and Transport, 2022; 35(12): 205–218.

Liu Y P, Cui T, Zhou C B, Li X C, Liu T. Abnormal Vehicle Detection Based on Improved Gaussian Mixture Model and Graph Handle. Computer Engineering and Science, 2020; 2020(2): 266–272. (in Chinese).

Ahn J, Lee Y, Kim M, Park J. Intersection Navigation in Unstructured Environment Using Multi-Task Network. Journal of Advanced Transportation, 2022; 2022: 1–13.

Liu Y G, Wang X, Li L, Cheng S, Chen Z. A Novel Lane Change Decisionmaking Model of Autonomous Vehicle based on Support Vector Machine. IEEE Access, 2019; 7: 26543–26550.

Varona B, Monteserin A, Teyseyre A. A Deep Learning Approach to Automatic Road Surface Monitoring and Pothole Detection. Pers Ubiquit Comput, 2020; 24: 519–534.

Yang X F, Li X T, Ye Y M, Lau R Y K, Zhang X F, Huang X H. Road detection and centerline extraction via deep recurrent convolutional neural network U-Net. IEEE Transactions on Geoence and Remote Sensing, 2019;

(9): 7209–7220.

Bolya D, Zhou C, Xiao F Y, Lee Y J. YOLACT: Real-time Instance Segmentation. 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Korea (South): IEEE, 2019; pp.9157–9166. doi: 10.1109/ICCV.2019.00925.

Qian Y, Dolan J M, Yang M. DLT-Net: Joint Detection of Drivable Areas, Lane Lines, and Traffic Objects. IEEE Transactions on Intelligent Transportation Systems; 2020, 21(11): 4670–4679.

Thakare K V, Sharma N, Dogra D P, Choi H, Kim I J. A multi-stream deep neural network with late fuzzy fusion for real-world anomaly detection. Expert Systems with Applications, 2022; 201: 117030.1–117030.13.

Yang W, Zhang X, Lei Q, Cheng X. Research on Longitudinal Active Collision Avoidance of Autonomous Emergency Braking Pedestrian System (AEB-P). Sensors, 2019; 19(21): 4671.1–4671.34.

Wu W L. An Intelligent Gray Prediction Model Based on Fuzzy Theory. International Transactions on Electrical Energy Systems, 2022; 25: 1–8.

Huang X Y, Wang P, Cheng X J, Zhou D F, Geng Q C, Yang R G. The ApolloScape Open Dataset for Autonomous Driving and Its Application. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020;

(10): 2702–2719.

Vaishaal S, Rebecca R, Horia M, Alex F, Benjamin R, Ludwig S. Evaluating Machine Accuracy on ImageNet. Proceedings of Machine Learning Research, 2020; 119: 8634–8644.

Kentaro Wada. labelme: Image Polygonal Annotation with Python. 2019. Available:https://github.com/wkentaro/labelme.

Marijn H, Anneroos P H. Machine Learning and the Platformization of the Military: A Study of Google’s Machine Learning Platform TensorFlow. International Political Sociology, 2022; 16(2): 1–19.

Campos C, Elvira E, Rodríguez J J G, Montiel J M M, Tardós J D. ORBSLAM3: An Accurate Open-Source Library for Visual, Visual–Inertial, and Multimap SLAM. IEEE Transactions on Robotics, 2021; 37(6):

–1890.

Wang J X, Zhao G C, Lu F N, Zhang G B, Ceng T, Qiao T R. Sphere geodesic octree grid method for true three-dimensional geological model construction. Journal of Geo-Information Science, 2019; 21(8): 1161–1169

(in Chinese).

Hodson T O. Root-mean-square error (RMSE) or mean absolute error (MAE): when to use them or not. Geosci. Model Dev, 2022; 15(14): 5481–5487.

Su Y Q, Cui C R, Qu H. Self-attentive moving average for time series prediction. Journal of Nanjing University (Natural Science), 2022; 4: 649–657.

Devon B, Nikolaos K, Rickard S, Jacek N. Automatic robust estimation for exponential smoothing: Perspectives from statistics and machine learning. Expert Systems with Applications, 2020; 160: 1–41.

Şahinli M A. Potato Price Forecasting with Holt-Winters and ARIMA Methods: A Case Study. Am. J. Potato Res, 2020; 97: 336–346.

Khan S, Hela A. ARIMA Model for Accurate Time Series Stocks Forecasting. International Journal of Advanced Computer Science and Applications, 2020; 11(7): 524–528.

Mor B, Garhwal S, Kumar A. A Systematic Review of Hidden Markov Models and Their Applications. Arch Computat Methods Eng, 2021; 28: 1429–1448.

Wickramasinghe I, Kalutarage H. Naive Bayes: applications, variations and vulnerabilities: a review of literature with code snippets for implementation. Soft Computing, 2021; 25: 2277–2293.

Mahdi S, Alexandra S L, Nilay S. Machine-learning methods for integrated renewable power generation: A comparative study of artificial neural networks, support vector regression, and Gaussian Process Regression.

Renewable and Sustainable Energy Reviews, 2019; 108: 513–538.

Ye X Y, Mao C L, Wang H S, Yuan S L. Research on Road Terrain Recognition based on Resnet-101 Deep Learning Network. Auto Time, 2021; 16: 30–31. (in Chinese)

Li Y, Qi H Z, Dai J F, Ji X Y, Wei Y C. Fully convolutional instanceaware semantic segmentation. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA: IEEE, 2017; pp.4438–4446. doi: 10.1109/CVPR.2017.472.

Huang Z J, Huang L C, Gong Y C, Huang C, Wang X G. Mask Scoring RCNN. 2019 IEEE/CVF Conference Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA: IEEE, 2019; pp.6409–6418.

doi: 10.1109/CVPR.2019.00657.

He K M, Gkioxari G, Dollár P, Girshick R. Mask R-CNN. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020; 2(42): 386–397.




Copyright (c) 2021 International Journal of Agricultural and Biological Engineering

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.

2023-2026 Copyright IJABE Editing and Publishing Office