Extraction and Research of Crop Feature Points Based on Computer Vision

Cui, Jingwen; Zhang, Jianping; Sun, Greg; Zheng, Bowen

doi:10.3390/s19112553

Cited by 10 publications

(9 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Here, VGG16 (Visual Geometry Group 16) [ 30 , 31 , 32 ], and the Inception v2 [ 33 ] algorithms are employed as feature extractors with Faster RCNN. Likewise, the YOLOv3 module makes use of Darknet-19 as a feature extractor [ 34 , 35 , 36 ]. The object detection algorithms are trained on the same image dataset and the same number of epochs.…”

Section: Resultsmentioning

confidence: 99%

AI Enabled IoRT Framework for Rodent Activity Monitoring in a False Ceiling Environment

Ramalingam

Tun²,

Mohan

et al. 2021

Sensors

View full text Add to dashboard Cite

Routine rodent inspection is essential to curbing rat-borne diseases and infrastructure damages within the built environment. Rodents find false ceilings to be a perfect spot to seek shelter and construct their habitats. However, a manual false ceiling inspection for rodents is laborious and risky. This work presents an AI-enabled IoRT framework for rodent activity monitoring inside a false ceiling using an in-house developed robot called "Falcon." The IoRT serves as a bridge between the users and the robots, through which seamless information sharing takes place. The shared images by the robots are inspected through a Faster RCNN ResNet 101 object detection algorithm, which is used to automatically detect the signs of rodent inside a false ceiling. The efficiency of the rodent activity detection algorithm was tested in a real-world false ceiling environment, and detection accuracy was evaluated with the standard performance metrics. The experimental results indicate that the algorithm detects rodent signs and 3D-printed rodents with a good confidence level.

show abstract

Section: Resultsmentioning

confidence: 99%

AI Enabled IoRT Framework for Rodent Activity Monitoring in a False Ceiling Environment

Ramalingam

Tun²,

Mohan

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Here, MobileNet and Inception v2 [ 45 ] classifiers were used with SSD for feature extraction task [ 46 , 47 , 48 ]. Similarly, darknet19 feature extractor is used in Yolo v2 module [ 49 , 50 , 51 ]. The three detection frameworks are trained with the same lizard and insect image dataset and similar amount of training time.…”

Section: Resultsmentioning

confidence: 99%

Remote Insects Trap Monitoring System Using Deep Learning Framework and IoT

Ramalingam

Mohan

Pookkuttath

et al. 2020

Sensors

View full text Add to dashboard Cite

Insect detection and control at an early stage are essential to the built environment (human-made physical spaces such as homes, hotels, camps, hospitals, parks, pavement, food industries, etc.) and agriculture fields. Currently, such insect control measures are manual, tedious, unsafe, and time-consuming labor dependent tasks. With the recent advancements in Artificial Intelligence (AI) and the Internet of things (IoT), several maintenance tasks can be automated, which significantly improves productivity and safety. This work proposes a real-time remote insect trap monitoring system and insect detection method using IoT and Deep Learning (DL) frameworks. The remote trap monitoring system framework is constructed using IoT and the Faster RCNN (Region-based Convolutional Neural Networks) Residual neural Networks 50 (ResNet50) unified object detection framework. The Faster RCNN ResNet 50 object detection framework was trained with built environment insects and farm field insect images and deployed in IoT. The proposed system was tested in real-time using four-layer IoT with built environment insects image captured through sticky trap sheets. Further, farm field insects were tested through a separate insect image database. The experimental results proved that the proposed system could automatically identify the built environment insects and farm field insects with an average of 94% accuracy.

show abstract

“…Figure A1a,b show an RGB color image and a depth image of an SSB, respectively. According to the 3D point cloud reconstruction process, 3D point clouds of the four SSBs with various diameters (30,40,50, and 60 cm) were reconstructed based on images captured by the Kinect sensor in three positions (P 1 , P 2 , and P 3 ) and at three combinations of AOVs (V 3 , V 4 , and V 6 ). In addition, a reference point cloud consisting of 90,000 points was constructed for each of the four SSBs.…”

Section: Appendix Amentioning

confidence: 99%

“…Stereoscopic vision [19,20], depth camera (Kinect sensor or TOF camera) [21][22][23][24][25], and 3D laser lidar [26][27][28] sensors can only capture two-and-a-half-dimensional (2.5D) depth images at a single angles of view (AOV). Kinect sensor-based 3D plant reconstruction can be divided into single-view [29][30][31] and multiview reconstruction [32][33][34], the latter mainly using the iterative closest point (ICP) algorithm [24,25]. However, we first need to solve the problem regarding the rough registration of multiview point clouds, otherwise ICP cannot be used for accurate registration.…”

Section: Introductionmentioning

confidence: 99%

Three-Dimensional Point Cloud Reconstruction and Morphology Measurement Method for Greenhouse Plants Based on the Kinect Sensor Self-Calibration

Sun

Wang

2019

Agronomy

View full text Add to dashboard Cite

Plant morphological data are an important basis for precision agriculture and plant phenomics. The three-dimensional (3D) geometric shape of plants is complex, and the 3D morphology of a plant changes relatively significantly during the full growth cycle. In order to make high-throughput measurements of the 3D morphological data of greenhouse plants, it is necessary to frequently adjust the relative position between the sensor and the plant. Therefore, it is necessary to frequently adjust the Kinect sensor position and consequently recalibrate the Kinect sensor during the full growth cycle of the plant, which significantly increases the tedium of the multiview 3D point cloud reconstruction process. A high-throughput 3D rapid greenhouse plant point cloud reconstruction method based on autonomous Kinect v2 sensor position calibration is proposed for 3D phenotyping greenhouse plants. Two red–green–blue–depth (RGB-D) images of the turntable surface are acquired by the Kinect v2 sensor. The central point and normal vector of the axis of rotation of the turntable are calculated automatically. The coordinate systems of RGB-D images captured at various view angles are unified based on the central point and normal vector of the axis of the turntable to achieve coarse registration. Then, the iterative closest point algorithm is used to perform multiview point cloud precise registration, thereby achieving rapid 3D point cloud reconstruction of the greenhouse plant. The greenhouse tomato plants were selected as measurement objects in this study. Research results show that the proposed 3D point cloud reconstruction method was highly accurate and stable in performance, and can be used to reconstruct 3D point clouds for high-throughput plant phenotyping analysis and to extract the morphological parameters of plants.

show abstract

Extraction and Research of Crop Feature Points Based on Computer Vision

Cited by 10 publications

References 25 publications

AI Enabled IoRT Framework for Rodent Activity Monitoring in a False Ceiling Environment

AI Enabled IoRT Framework for Rodent Activity Monitoring in a False Ceiling Environment

Remote Insects Trap Monitoring System Using Deep Learning Framework and IoT

Three-Dimensional Point Cloud Reconstruction and Morphology Measurement Method for Greenhouse Plants Based on the Kinect Sensor Self-Calibration

Contact Info

Product

Resources

About