リケラボ論文検索は、全国の大学リポジトリにある学位論文・教授論文を一括検索できる論文検索サービスです。

リケラボ 全国の大学リポジトリにある学位論文・教授論文を一括検索するならリケラボ論文検索大学・研究所にある論文を検索できる

リケラボ 全国の大学リポジトリにある学位論文・教授論文を一括検索するならリケラボ論文検索大学・研究所にある論文を検索できる

大学・研究所にある論文を検索できる 「ステレオビジョンカメラによる再構成路面情報に基づくトラクタの挙動予測」の論文概要。リケラボ論文検索は、全国の大学リポジトリにある学位論文・教授論文を一括検索できる論文検索サービスです。
リケラボ

コピーが完了しました

URLをコピーしました

論文の公開元へ論文の公開元へ
書き出し

ステレオビジョンカメラによる再構成路面情報に基づくトラクタの挙動予測

愼, 素煐 SHIN, SOYOUNG シン, ソヨン 九州大学

2020.09.25

概要

With the decrease in agricultural population and the increase in large-scale farmland, the use of agricultural machinery is indispensable, therefore, a research on improving the safety of agricultural machinery is required. In particular, tractor rollover accident, which suffered the most casualties, is one of the most attracting problems. Tractors with a high center of gravity compared to other vehicles are easily exposed to the risk of tipping over. Furthermore, tractors that mainly drive on uneven roads have a very high risk of overturning. The tractor overturn accident is affected by various factors such as whether the implements are attached, the location of the attached implements, the soil condition, and the operation speed.

Statistically, the tractor rollover accident was about 75-85% of the side rollover, and it was found that the tractor mainly occurred on uneven sloped roads. A number of prominent research observed basic phenomena and defined fundamental theories on tractor rollover. In order to reduce the human injury caused by rollover, the rollover protective structure(ROPS) was designed and developed. ROPS was able to reduce fatalities by protecting the space in the driver's seat when a tractor rollover occurred. However, ROPS does not prevent actual accidents. In order to replace this passive method, theoretical mathematical modelling of the tractor behaviour characteristics, ground characteristics, and vehicle stability has been developed. By using models of physically static, semi-static, and dynamic states, the characteristics of the tractor can be considered when driving. The tractor's mathematical modelling was used to develop the tractor's safety indicators. Several research derived equations of up and down, pitching, rolling, and forward and backward motions of tractors driving on inclined terrain, and simulated tractor motion on the actual form of rollover accidents site. In this study, we aim to predict the correct behavior based on the tractor dynamics model, consider to establish early roll behavior prediction system when operating on roads and bumps using the tractor angular velocity. Moreover, for the purpose of indicating the actual condition of the tractor driving on the road surface, the estimation of the state was performed with the extended Kalman filter between the simulation values and measured values. In order to effectively prevent the tractor from tipping over, it is important to confirm the predicted rollover before the tractor actually drives upcoming road. In this study, the stereo-vision camera installed on the tractor reconstructs the front ground of the tractor in three dimensions and the reconstructed ground information entered into the tractor motion model to predict the tractor's rollover. The same ground taken from different angles can be reconstructed in three dimensions. Using the stereo-vision camera on this principle, it is possible to obtain reliable three-dimensional data with paired two-dimensional images. The distance to the target object can be identified by collecting 3D data. 3D reconstruction using stereo-vision becomes attractive method to providing adequate details. Through this, in agriculture field, stereo-vision camera adopted to the crop harvesting robots, and it is mainly used to grasp the growth status of indoor cultivated crops and observe obstacles. A study was also conducted to establish a machine stop system for preventing a safety accident when a person or obstacle is predicted by estimating the situation ahead using a stereo-vision camera.

Chapter 2 presents the study on the terrain reconstruction using stereo-vision camera. A fundamental knowledge of stereoscopic was introduced, and the usefulness of stereo-vision camera for terrain reconstruction was evaluated in this chapter. The reconstructed grounds with the stereo-vision camera were investigated, and the 3D reconstruction of the stereo vision camera to which the gimbal system was applied was compared the error level.

Chapter 3 describes the behaviour model of the tractor driving the slope and the key assumptions employed to derive the model. Based on the derived equations of motion, we introduced the existing programs developed using Matlab/Simulink. Using the simulation model, each result when driving on the reconstructed ground was investigated and the usefulness of the model was considered.

In Chapter 4, the extended Kalman filter was introduced and the application of the Extended Kalman filter to improve simulation accuracy was investigated. This chapter will introduce an improvement in the accuracy of model estimation and model estimation by filtering using the estimated value by the model and the measured value of the angular velocity obtained from the inertial sensor.

The major results and implications of this study are summarized in Chapter 5.

論文の公開元へ

この論文で使われている画像

関連論文

関連論文をもっと見る

参考文献

Abubakar, M. S., Ahmad, D., & Akande, F. B. (2010). A review of farm tractor overturning accidents and safety. Pertanika Journal of Science and Technology, 18(2), 377-385.

Agarwal, Pankaj K., Lars Arge, & Andrew Danner. (2006). From point cloud to grid DEM: A scalable approach. Progress in Spatial Data Handling. Springer, Berlin, Heidelberg. 771-788.

Agrawal, M., Konolige, K., & Bolles, R. C. (2007). Localization and mapping for autonomous navigation in outdoor terrains: A stereo vision approach. In 2007 IEEE Workshop on Applications of Computer Vision (WACV'07) (pp. 7-7). IEEE.

Ahmandi, I. (2013). Development of a tractor dynamic stability index calculator utilizing some tractor specifications. Turkish Journal of Agriculture and Forestry, 37(2), 203- 211.

Aoyagi, Y., Matsui, M., Morio, D., Tamura, T., Uchikawa, T., Kumra, T. (2016). Study on Tractor Behavior Based on Accident Topography. Journal of the Japanese Society of Agricultural Machinery and Food Engineers, 78(6), 529-535.

Baker, V., & Guzzomi, A. L. (2013). A model and comparison of 4-wheel-drive fixed- chassis tractor rollover during Phase I. Biosystems Engineering, 116(2), 179-189.

Borodin, V. M., Spiridonov, I. O., & Faizutdinov, R. N. (2016). Analysis of dynamics of a passive line-of-sight stabilization system with four-axis gimbal suspension. Russian Aeronautics, 59(4), 480-488.

Broggi, A., Caraffi, C., Fedriga, R. I., & Grisleri, P. (2005). Obstacle detection with stereo vision for off-road vehicle navigation. In 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)-Workshops. 65.

Cantón, J., Donaire, J., & Sánchez-Hermosilla, J. (2012). Stereovision based software to estimate crop parameters in greenhouses. In Proceeding of Infomation Technology, Automation and Precision Farming. International Conference of Agricultural Engineering-CIGR-AgEng: Agriculture and Engineering for a Healthier Life. 8-12. Chen, C., Yang, B. S., & Song, S. (2016). Low cost and efficient 3d indoor mapping using multiple consumer RGB-D cameras. International Archives of the Photogrammetry, Remote Sensing & Spatial Information Sciences, 41.

Chisholm, C. J. (1979). The effect of parameter variation on tractor overturning and impact behavior. Journal of Agricultural Engineering Research, 24(4), 417-440.

Choe, J.S., Akimune, H., Shin, S., Inoue, E., Mitsuoka, M., Okayasu, T., Hirai, Y. (2019). Behavior simulation of tractor driven on slopes and undulating roads. Journal of the Faculty of Agriculture Kyushu University, 64(1), 157-162.

Chou, T., & Chu, T. W. (2014). An improvement in rollover detection of articulated vehicles using the grey system theory. Vehicle system dynamics, 52(5), 679-703.

Government of Japan, 2013. Japan Revitalization Strategy: Japan Is Back. Provisional report. Available at http://www.kantei.go.jp/jp/singi/keizaisaisei/pdf/en_saikou_jpn_hon.pdf. (Accessed: 2019.04.05).

Grattoni, P., Cumani, A., Guiducci, A., & Pettiti, G. (1994). Automatic harvesting of asparagus: An application of robot vision to agriculture. International Society for Optics and Photonics. In Mobile Robots VIII 2058, 200-210.

Guzzomi, A. L., Rondelli, V., Guarnieri, A., Molari, G., & Molari, P. G. (2009). Available energy during the rollover of narrow-track wheeled agricultural tractors. Biosystems Engineering, 104(3), 318-323.

Guzzomi, A. L. (2012). A revised kineto-static model for Phase I tractor rollover. Biosystems Engineering, 113(1), 65-75.

Hammoudi, K., Dornaika, F., Soheilian, B., & Paparoditis, N. (2010). Extracting wire- frame models of street facades from 3D point clouds and the corresponding cadastral map. IAPRS, 38(Part 3A), 91-96.

Harayama, Y. (2017). Report on Artificial Intelligence and Human Society. Advisory Board on AI and Human Society, Council for Science, Technology and Innovation, The Cabinet Office of Japan.

Herdt, R.W. (1983). Mechanization of rice production in developing Asian countries: Perspective, evidence and issues. In: Consequences of Small Farm Mechanization. International Rice Research Institute, Los Baños, Laguna, Philippines.

Henry, P., Krainin, M., Herbst, E., Ren, X., & Fox, D. (2014). RGB-D mapping: Using depth cameras for dense 3D modeling of indoor environments. In Experimental robotics, 477-491.

Kanazawa, Y., & Kanatani, K. (1995). Reliability of 3-D reconstruction by stereo vision. IEICE TRANSACTIONS on Information and Systems, 78(10), 1301-1306.

Kang, H., Li, H., Zhang, J., Lu, X., & Benes, B. (2018). Flycam: Multitouch gesture controlled drone gimbal photography. IEEE Robotics and Automation Letters, 3(4), 3717-3724.

Kisu, M. (1983). Mechanization of rice farming. In: Farm Mechanization in Asia. Asian Productivity Organization, Tokyo, Japan.

Kitamura, S., & Oka, K. (2005). Recognition and cutting system of sweet pepper for picking robot in greenhouse horticulture. In IEEE International Conference Mechatronics and Automation, 4, 1807-1812.

Lati, R. N., Filin, S., & Eizenberg, H. (2013). Estimating plant growth parameters using an energy minimization-based stereovision model. Computers and Electronics in Agriculture, 98, 260-271.

Li, Z., Mitsuoka, M., Inoue, E., Okayasu, T., Hirai, Y., & Zhu, Z. (2015a). Modification of a tractor dynamic model considering the rotatable front end. Journal of the Faculty of Agriculture, Kyushu Univeristy, 60(1), 219-224.

Li, Z., Mitsuoka, M., Inoue, E., Okayasu, T., Hirai, Y., & Zhu, Z. (2015b). Prediction of tractor sideslipping behabior using a quasi-static model. Journal of the Faculty of Agriculture, Kyushu University, 60(1), 215-218.

Liu, B., & Koc, A. B. (2015). Field tests of a tractor rollover detection and emergency notification system. Journal of agricultural safety and health, 21(2), 113-127.

Liu, J., & Ayers, P. (1999). Off-road vehicle rollover and field testing of stability index. Journal of agricultural safety and health, 5(1), 59.

Mashadi, B., & Nasrolahi, H. (2009). Automatic control of a modified tractor to work on steep side slopes. Journal of Terramechanics, 46(6), 299-311.

Michihisa, I. I. D. A., ASADA, R., ZHANG, Y., SUGURI, M., & MASUDA, R. (2018). Obstacle Detection and Avoidance for Autonomous Combine Harvester. In 2018 ASABE Annual International Meeting (p. 1). American Society of Agricultural and Biological Engineers.

Ministry of Agriculture, Forestry and Fisheries of Japan. Report on fatal farming accidents that happened in 2013 (in Japanese). Available from https://www.maff.go.jp/j/seisan/sien/sizai/s_kikaika/anzen/pdf/25sibou.pdf. (Accessed: 2019.04.05).

Ministry of Agriculture, Forestry and Fisheries of Japan. Report on fatal farming accidents that happened in 2014 (in Japanese). Available from https://www.maff.go.jp/j/seisan/sien/sizai/s_kikaika/anzen/pdf/26sibo.pdf. (Accessed: 2019.04.05).

Ministry of Agriculture, Forestry and Fisheries of Japan. Report on fatal farming accidents that happened in 2015 (in Japanese). Available from https://www.maff.go.jp/j/seisan/sien/sizai/s_kikaika/anzen/attach/pdf/index-18.pdf. (Accessed: 2019.04.05).

Ministry of Agriculture, Forestry and Fisheries of Japan. Report on fatal farming accidents that happened in 2016 (in Japanese). Available from https://www.maff.go.jp/j/seisan/sien/sizai/s_kikaika/anzen/attach/pdf/index-52.pdf. (Accessed: 2019.04.05).

Ministry of Agriculture, Forestry and Fisheries of Japan. Report on fatal farming accidents that happened in 2017 (in Japanese). Available from https://www.maff.go.jp/j/seisan/sien/sizai/s_kikaika/anzen/attach/pdf/sibo-5.pdf. (Accessed: 2019.04.05).

Ministry of Agriculture, Forest and Fisheries, 2017. Reports on the number of agricultural business farmers and the number of owned tractors. Available from https://www.maff.go.jp/j/tokei/census/afc2015/280624.html. (Accessed: 2019.04.05).

Mohammed A, Z. (2017). Automatic plant features recognition using stereo vision for crop monitoring (Doctoral dissertation, University of Southern Queensland).

Murray, D., & Little, J. J. (2000). Using real-time stereo vision for mobile robot navigation. autonomous robots, 8(2), 161-171.

Nedevschi, S., Danescu, R., Frentiu, D., Marita, T., Oniga, F., Pocol, C., Schmidt, R., & Graf, T. (2004). High accuracy stereo vision system for far distance obstacle detection. In IEEE Intelligent Vehicles Symposium, 292-297.

Nichol, C. I., Sommer Ⅲ, H. J., & Murphy, D. J. (2005). Simplified overturn stability monitoring of agricultural tractors. Journal of Agricultural Safety and Health, 11(1), 99-108.

Ortiz, L. E., Cabrera, E. V., & Gonçalves, L. M. (2018). Depth data error modeling of the ZED 3D vision sensor from stereolabs. ELCVIA: electronic letters on computer vision and image analysis, 17(1), 0001-15.

Previati, G., Gobbi, M., & Mastinu, G. (2014). Mathematical models for farm tractor rollover prediction. International journal of vehicle design, 64(2-4), 280-303.

Rhee, S., J. Jung, & T. Kim, (2009). DEM Generation from kompsat-2 images and accuracy comparison by using common software, Korean Journal of Remote Sensing, 25(4): 359-366 (in Korean with English abstract).

Rhee, S., J. Jung, & T. Kim, (2011). DEM Generation from kompsat-2 images and accuracy comparison by from multiple Kompsat-2 images, Korean Journal of Remote Sensing, 27(1): 51-58 (in Korean with English abstract)

Rondelli, V., Vasazza, C., & Martelli, R. (2018). Tractor rollover fatalities, analyzing accident scenario. Journal of safety research, 67, 99-106.

Rondelli, V., Vasazza, C., & Martelli, R. (2018). Tractor rollover fatalities, analyzing accident scenario. Journal of safety research, 67, 99-106.

Si, Y., Liu, G., & Feng, J. (2015). Location of apples in trees using stereoscopic vision. Computers and Electronics in Agriculture, 112, 68-74.

Srivastava, A. K., Rehkugler, G. E., & Masemore, B. J. (1978). Similitude modeling applied to ROPS testing. Transactions of the ASAE, 21(4), 633-0645.

Sun, D., Chen, D., Wang, S., & Wang, X. (2016). A dynamic instability detection and prediction system for high clearance tractor. IFAC-PapersOnLine, 49(16), 50-54.

Tauro, F., Porfiri, M., & Grimaldi, S. (2016). Surface flow measurements from drones. Journal of Hydrology, 540, 240-245.

Whitehorn, M., Vincent, T., Debrunner, C. H., & Steele, J. (2003). Stereo vision in LHD automation. IEEE Transactions on Industry Applications, 39(1), 21-29.

Zhu, Z., & Donia, S. (2013a). Potentials of RGB-D cameras in as-built indoor environment modeling. In Computing in Civil Engineering, 605-612.

Zhu, Z., & Donia, S. (2013b). Spatial and visual data fusion for capturing, retrieval, and modeling of as-built building geometry and features. Visualization in Engineering, 1(1), 1-10.

参考文献をもっと見る

全国の大学の
卒論・修論・学位論文
を
一発検索！

この論文の関連論文を見る