Feature Point Registration Model of Farmland Surface and Its Application Based on a Monocular Camera

Li, Yang; Huang, Dazhi; Qi, Jiangtao; Chen, Sikai; Sun, Huibin; Liu, Huili; Hu, Jia

doi:10.3390/s20133799

Cited by 8 publications

(5 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Though deep information may miss during this process, massive texture details can be maintained on the image planes [23] . Wang et al [24] judged whether there were ridges according to the leap characteristics of pixel grayscale inside and outside farmland based on machine vision technology, and acquired the main extension azimuth line of the actual irregular ridge boundaries by evenly dividing the image into 8 sub processing regions along the horizontal direction. Then they moved the main extension azimuth line downward and parallel so as to acquire the boundaries for agricultural machineries to safely turn around at the current ridge.…”

Section: Image-based Sensorsmentioning

confidence: 99%

Review of the field environmental sensing methods based on multi-sensor information fusion technology

Yuanyuan,

Bin,

Cheng

et al. 2024

International Journal of Agricultural and Biological Engineering

View full text Add to dashboard Cite

Field environmental sensing can acquire real-time environmental information, which will be applied to field operation, through the fusion of multiple sensors. Multi-sensor fusion refers to the fusion of information obtained from multiple sensors using more advanced data processing methods. The main objective of applying this technology in field environment perception is to acquire real-time environmental information, making agricultural mechanical devices operate better in complex farmland environment with stronger sensing ability and operational accuracy. In this paper, the characteristics of sensors are studied to clarify the advantages and existing problems of each type of sensors and point out that multiple sensors can be introduced to compensate for the information loss. Secondly, the mainstream information fusion types at present are outlined. The characteristics, advantages and disadvantages of different fusion methods are analyzed. The important studies and applications related to multi-sensor information fusion technology published at home and abroad are listed. Eventually, the existing problems in the field environment sensing at present are summarized and the prospect for future of sensors precise sensing, multi-dimensional fusion strategies, discrepancies in sensor fusion and agricultural information processing are proposed in hope of providing reference for the deeper development of smart agriculture.

show abstract

Section: Image-based Sensorsmentioning

confidence: 99%

Review of the field environmental sensing methods based on multi-sensor information fusion technology

Yuanyuan,

Bin,

Cheng

et al. 2024

International Journal of Agricultural and Biological Engineering

View full text Add to dashboard Cite

show abstract

“…It turns to the next row when another feature indicating the end of the row is recognised. (English et al, 2014;Li et al, 2020b;Papadakis, 2013;Rabab et al, 2021;Zhai et al, 2016;Zhang et al, 2022). This simple idea is just kin to autonomous guided vehicles used in warehouses, factories, and controlled hazardous zones.…”

Section: Literature Reviewmentioning

confidence: 99%

Implementation of autonomous mobile platform for agricultural task in corridor-like environments

Tobias,

Lim,

Duke

et al. 2024

Preprint

View full text Add to dashboard Cite

The role of autonomous vehicles (AVs) in assisting people is recognised and, therefore, is in constant development in numerous fields. Specifically, the ability of AV to alleviate global stressors, including an increased potential for food shortages and the decline in workers for potentially laborious work. An area where AVs developments are particularly prevalent is in agriculture. However, the few AVs being used in agriculture are often custom-built for specific purposes and require long development time as a result. This article aims to build and evaluate a versatile architecture of a mobile platform that is implemented using off-the-shelf components so that it can be transferred to any agricultural vehicle, thus reducing the development time. The research has involved investigating and incorporating various sensors, and also developing a common software module to perform the localisation, navigation and mapping particularly suited for corridor crop agricultural environment. This architecture has been integrated and implemented on a Yamaha golf cart, infusing it with purposely positioned sensors and supportive electronics to allow a Robotic Operating System (ROS) framework to gather information and control the vehicle. As the architecture is modular in nature, it can be transferred to different customised platforms. To determine the efficacy of the mobile platform, it has gone through several outdoor field trials to test the fundamentals of an agricultural AV. The evaluation demonstrates that both mapping and navigation have satisfactory results and the mobile platform remains within 5mm of the specified distance when aiming to follow the row in a vineyard. The results from these experiments demonstrate the ability of the mobile platform to successfully transform a Yamaha golf cart into an autonomous agricultural vehicle.

show abstract

“…Since a decrease in the number of feature points leads to easier mismatching, increasing the distinguishability of the feature points can be used to increase the quality of each feature point at the same time. The Features from Accelerated Segment Test (FAST) algorithm [ 31 ] is a highly efficient feature detection method that can be updated almost in real time by recognizing corners as features. This was employed in this paper to increase the initial threshold of FAST to build up better feature points and decrease the minimum threshold.…”

Section: Multi-sensor Fusion-based System Structurementioning

confidence: 99%

Multi-Sensor Fusion Simultaneous Localization Mapping Based on Deep Reinforcement Learning and Multi-Model Adaptive Estimation

Wong,

Feng,

Kuo

2023

Sensors

View full text Add to dashboard Cite

In this study, we designed a multi-sensor fusion technique based on deep reinforcement learning (DRL) mechanisms and multi-model adaptive estimation (MMAE) for simultaneous localization and mapping (SLAM). The LiDAR-based point-to-line iterative closest point (PLICP) and RGB-D camera-based ORBSLAM2 methods were utilized to estimate the localization of mobile robots. The residual value anomaly detection was combined with the Proximal Policy Optimization (PPO)-based DRL model to accomplish the optimal adjustment of weights among different localization algorithms. Two kinds of indoor simulation environments were established by using the Gazebo simulator to validate the multi-model adaptive estimation localization performance, which is used in this paper. The experimental results of the proposed method in this study confirmed that it can effectively fuse the localization information from multiple sensors and enable mobile robots to obtain higher localization accuracy than the traditional PLICP and ORBSLAM2. It was also found that the proposed method increases the localization stability of mobile robots in complex environments.

show abstract

Feature Point Registration Model of Farmland Surface and Its Application Based on a Monocular Camera

Cited by 8 publications

References 24 publications

Review of the field environmental sensing methods based on multi-sensor information fusion technology

Review of the field environmental sensing methods based on multi-sensor information fusion technology

Implementation of autonomous mobile platform for agricultural task in corridor-like environments

Multi-Sensor Fusion Simultaneous Localization Mapping Based on Deep Reinforcement Learning and Multi-Model Adaptive Estimation

Contact Info

Product

Resources

About