Single Shot MultiBox Detector for Urban Plantation Single Tree Detection and Location With High-Resolution Remote Sensing Imagery

Using high-resolution remote sensing images to automatically identify individual trees is of great significance to forestry ecological environment monitoring. Urban plantation has realistic demands for single tree management such as catkin pollution, maintenance of famous trees, landscape construction, and park management. At present, there are problems of missed detection and error detection in dense plantations and complex background plantations. This paper proposes a single tree detection method based on single shot multibox detector (SSD). Optimal SSD is obtained by adjusting feature layers, optimizing the aspect ratio of a preset box, reducing parameters and so on. The optimal SSD is applied to single tree detection and location in campuses, orchards, and economic plantations. The average accuracy based on SSD is 96.0, 92.9, and 97.6% in campus green trees, lychee plantations, and palm plantations, respectively. It is 11.3 and 37.5% higher than the latest template matching method and chan-vese (CV) model method, and is 43.1 and 54.2% higher than the traditional watershed method and local maximum method. Experimental results show that SSD has a strong potential and application advantage. This research has reference significance for the application of an object detection framework based on deep learning in agriculture and forestry.

Download Full-text

YOLOv4-Lite–Based Urban Plantation Tree Detection and Positioning With High-Resolution Remote Sensing Imagery

Frontiers in Environmental Science ◽

10.3389/fenvs.2021.756227 ◽

2022 ◽

Vol 9 ◽

Author(s):

Yueyuan Zheng ◽

Gang Wu

Keyword(s):

Remote Sensing ◽

High Resolution ◽

Object Detection ◽

Template Matching ◽

Large Scale ◽

Local Maximum ◽

High Rate ◽

Detection Methods ◽

Tree Detection ◽

Single Tree

Automatic tree identification and position using high-resolution remote sensing images are critical for ecological garden planning, management, and large-scale environmental quality detection. However, existing single-tree detection methods have a high rate of misdetection in forests not only due to the similarity of background and crown colors but also because light and shadow caused abnormal crown shapes, resulting in a high rate of misdetections and missed detection. This article uses urban plantations as the primary research sample. In conjunction with the most recent deep learning method for object detection, a single-tree detection method based on the lite fourth edition of you only look once (YOLOv4-Lite) was proposed. YOLOv4’s object detection framework has been simplified, and the MobileNetv3 convolutional neural network is used as the primary feature extractor to reduce the number of parameters. Data enhancement is performed for categories with fewer single-tree samples, and the loss function is optimized using focal loss. The YOLOv4-Lite method is used to detect single trees on campus, in an orchard, and an economic plantation. Not only is the YOLOv4-Lite method compared to traditional methods such as the local maximum value method and the watershed method, where it outperforms them by nearly 46.1%, but also to novel methods such as the Chan-Vese model and the template matching method, where it outperforms them by nearly 26.4%. The experimental results for single-tree detection demonstrate that the YOLOv4-Lite method improves accuracy and robustness by nearly 36.2%. Our work establishes a reference for the application of YOLOv4-Lite in additional agricultural and plantation products.

Download Full-text

Single-Tree Detection in High-Resolution Remote-Sensing Images Based on a Cascade Neural Network

ISPRS International Journal of Geo-Information ◽

10.3390/ijgi7090367 ◽

2018 ◽

Vol 7 (9) ◽

pp. 367 ◽

Cited By ~ 7

Author(s):

Dong Tianyang ◽

Zhang Jian ◽

Gao Sibin ◽

Shen Ying ◽

Fan Jing

Keyword(s):

Neural Network ◽

Remote Sensing ◽

High Resolution ◽

Bp Neural Network ◽

Detection Method ◽

Detection Methods ◽

Remote Sensing Images ◽

Tree Detection ◽

Single Tree ◽

Cascade Neural Network

Traditional single-tree detection methods usually need to set different thresholds and parameters manually according to different forest conditions. As a solution to the complicated detection process for non-professionals, this paper presents a single-tree detection method for high-resolution remote-sensing images based on a cascade neural network. In this method, we firstly calibrated the tree and non-tree samples in high-resolution remote-sensing images to train a classifier with the backpropagation (BP) neural network. Then, we analyzed the differences in the first-order statistic features, such as energy, entropy, mean, skewness, and kurtosis of the tree and non-tree samples. Finally, we used these features to correct the BP neural network model and build a cascade neural network classifier to detect a single tree. To verify the validity and practicability of the proposed method, six forestlands including two areas of oil palm in Thailand, and four areas of small seedlings, red maples, or longan trees in China were selected as test areas. The results from different methods, such as the region-growing method, template-matching method, BP neural network, and proposed cascade-neural-network method were compared considering these test areas. The experimental results show that the single-tree detection method based on the cascade neural network exhibited the highest root mean square of the matching rate (RMS_Rmat = 90%) and matching score (RMS_M = 68) in all the considered test areas.

Download Full-text

Single tree detection in very high resolution remote sensing data

Remote Sensing of Environment ◽

10.1016/j.rse.2007.02.029 ◽

2007 ◽

Vol 110 (4) ◽

pp. 533-544 ◽

Cited By ~ 96

Author(s):

M HIRSCHMUGL ◽

M OFNER ◽

J RAGGAM ◽

M SCHARDT

Keyword(s):

Remote Sensing ◽

High Resolution ◽

Remote Sensing Data ◽

Sensing Data ◽

Tree Detection ◽

Single Tree ◽

Very High

Download Full-text

Individual Tree Position Extraction and Structural Parameter Retrieval Based on Airborne LiDAR Data: Performance Evaluation and Comparison of Four Algorithms

Remote Sensing ◽

10.3390/rs12030571 ◽

2020 ◽

Vol 12 (3) ◽

pp. 571 ◽

Cited By ~ 2

Author(s):

Chen ◽

Xiang ◽

Moriya

Keyword(s):

Template Matching ◽

Local Maximum ◽

Airborne Lidar ◽

Forest Monitoring ◽

Lidar Data ◽

Individual Tree ◽

Matching Algorithm ◽

Crown Width ◽

Individual Trees ◽

Airborne Lidar Data

Information for individual trees (e.g., position, treetop, height, crown width, and crown edge) is beneficial for forest monitoring and management. Light Detection and Ranging (LiDAR) data have been widely used to retrieve these individual tree parameters from different algorithms, with varying successes. In this study, we used an iterative Triangulated Irregular Network (TIN) algorithm to separate ground and canopy points in airborne LiDAR data, and generated Digital Elevation Models (DEM) by Inverse Distance Weighted (IDW) interpolation, thin spline interpolation, and trend surface interpolation, as well as by using the Kriging algorithm. The height of the point cloud was assigned to a Digital Surface Model (DSM), and a Canopy Height Model (CHM) was acquired. Then, four algorithms (point-cloud-based local maximum algorithm, CHM-based local maximum algorithm, watershed algorithm, and template-matching algorithm) were comparatively used to extract the structural parameters of individual trees. The results indicated that the two local maximum algorithms can effectively detect the treetop; the watershed algorithm can accurately extract individual tree height and determine the tree crown edge; and the template-matching algorithm works well to extract accurate crown width. This study provides a reference for the selection of algorithms in individual tree parameter inversion based on airborne LiDAR data and is of great significance for LiDAR-based forest monitoring and management.

Download Full-text

Detection of Tailings Dams Using High-Resolution Satellite Imagery and a Single Shot Multibox Detector in the Jing–Jin–Ji Region, China

Remote Sensing ◽

10.3390/rs12162626 ◽

2020 ◽

Vol 12 (16) ◽

pp. 2626 ◽

Cited By ~ 1

Author(s):

Qingting Li ◽

Zhengchao Chen ◽

Bing Zhang ◽

Baipeng Li ◽

Kaixuan Lu ◽

...

Keyword(s):

Remote Sensing ◽

Deep Learning ◽

High Resolution ◽

Satellite Imagery ◽

Spatial Scales ◽

Detection Accuracy ◽

Single Shot ◽

Tailings Dams ◽

High Resolution Satellite Imagery ◽

Tailings Ponds

The timely and accurate mapping and monitoring of mine tailings dams is crucial to the improvement of management practices by decision makers and to the prevention of disasters caused by failures of these dams. Due to the complex topography, varying geomorphological characteristics, and the diversity of ore types and mining activities, as well as the range of scales and production processes involved, as they appear in remote sensing imagery, tailings dams vary in terms of their scale, color, shape, and surrounding background. The application of high-resolution satellite imagery for automatic detection of tailings dams at large spatial scales has been barely reported. In this study, a target detection method based on deep learning was developed for identifying the locations of tailings ponds and obtaining their geographical distribution from high-resolution satellite imagery automatically. Training samples were produced based on the characteristics of tailings ponds in satellite images. According to the sample characteristics, the Single Shot Multibox Detector (SSD) model was fine-tuned during model training. The results showed that a detection accuracy of 90.2% and a recall rate of 88.7% could be obtained. Based on the optimized SSD model, 2221 tailing ponds were extracted from Gaofen-1 high resolution imagery in the Jing–Jin–Ji region in northern China. In this region, the majority of tailings ponds are located at high altitudes in remote mountainous areas. At the city level, the tailings ponds were found to be located mainly in Chengde, Tangshan, and Zhangjiakou. The results prove that the deep learning method is very effective at detecting complex land-cover features from remote sensing images.

Download Full-text

Influence of river channel morphology and bank characteristics on water surface boundary delineation using high-resolution passive remote sensing and template matching

Earth Surface Processes and Landforms ◽

10.1002/esp.3560 ◽

2014 ◽

Vol 39 (7) ◽

pp. 977-986 ◽

Cited By ~ 9

Author(s):

İnci Güneralp ◽

Anthony M. Filippi ◽

Billy Hales

Keyword(s):

Remote Sensing ◽

High Resolution ◽

Template Matching ◽

Water Surface ◽

Channel Morphology ◽

River Channel ◽

Surface Boundary ◽

Passive Remote Sensing ◽

River Channel Morphology

Download Full-text

Comparison of Classical Methods and Mask R-CNN for Automatic Tree Detection and Mapping Using UAV Imagery

Remote Sensing ◽

10.3390/rs14020295 ◽

2022 ◽

Vol 14 (2) ◽

pp. 295

Author(s):

Kunyong Yu ◽

Zhenbang Hao ◽

Christopher J. Post ◽

Elena A. Mikhailova ◽

Lili Lin ◽

...

Keyword(s):

Remote Sensing ◽

Deep Learning ◽

Plantation Forest ◽

Remote Sensing Images ◽

Individual Tree ◽

Tree Detection ◽

Band Combination ◽

Individual Trees ◽

Lm Algorithm ◽

Multi Band

Detecting and mapping individual trees accurately and automatically from remote sensing images is of great significance for precision forest management. Many algorithms, including classical methods and deep learning techniques, have been developed and applied for tree crown detection from remote sensing images. However, few studies have evaluated the accuracy of different individual tree detection (ITD) algorithms and their data and processing requirements. This study explored the accuracy of ITD using local maxima (LM) algorithm, marker-controlled watershed segmentation (MCWS), and Mask Region-based Convolutional Neural Networks (Mask R-CNN) in a young plantation forest with different test images. Manually delineated tree crowns from UAV imagery were used for accuracy assessment of the three methods, followed by an evaluation of the data processing and application requirements for three methods to detect individual trees. Overall, Mask R-CNN can best use the information in multi-band input images for detecting individual trees. The results showed that the Mask R-CNN model with the multi-band combination produced higher accuracy than the model with a single-band image, and the RGB band combination achieved the highest accuracy for ITD (F1 score = 94.68%). Moreover, the Mask R-CNN models with multi-band images are capable of providing higher accuracies for ITD than the LM and MCWS algorithms. The LM algorithm and MCWS algorithm also achieved promising accuracies for ITD when the canopy height model (CHM) was used as the test image (F1 score = 87.86% for LM algorithm, F1 score = 85.92% for MCWS algorithm). The LM and MCWS algorithms are easy to use and lower computer computational requirements, but they are unable to identify tree species and are limited by algorithm parameters, which need to be adjusted for each classification. It is highlighted that the application of deep learning with its end-to-end-learning approach is very efficient and capable of deriving the information from multi-layer images, but an additional training set is needed for model training, robust computer resources are required, and a large number of accurate training samples are necessary. This study provides valuable information for forestry practitioners to select an optimal approach for detecting individual trees.

Download Full-text