EFFECTIVENESS OF U-NET IN DENOISING RGB IMAGES

The detection of spherical targets in workpiece shape clustering and fruit classification tasks is challenging. Spherical targets produce low detection accuracy in complex fields, and single-feature processing cannot accurately recognize spheres. Therefore, a novel spherical descriptor (SD) for contour fitting and convex hull processing is proposed. The SD achieves image de-noising by combining flooding processing and morphological operations. The number of polygon-fitted edges is obtained by convex hull processing based on contour extraction and fitting, and two RGB images of the same group of objects are obtained from different directions. The two fitted edges of the same target object obtained at two RGB images are extracted to form a two-dimensional array. The target object is defined as a sphere if the two values of the array are greater than a custom threshold. The first classification result is obtained by an improved K-NN algorithm. Circle detection is then performed on the results using improved Hough circle detection. We abbreviate it as a new Hough transform sphere descriptor (HSD). Experiments demonstrate that recognition of spherical objects is obtained with 98.8% accuracy. Therefore, experimental results show that our method is compared with other latest methods, HSD has higher identification accuracy than other methods.

Download Full-text

Semi-Automatic Fractional Snow Cover Monitoring from Near-Surface Remote Sensing in Grassland

Remote Sensing ◽

10.3390/rs13112045 ◽

2021 ◽

Vol 13 (11) ◽

pp. 2045

Author(s):

Anaí Caparó Bellido ◽

Bradley C. Rundquist

Keyword(s):

Snow Cover ◽

Near Infrared ◽

Accuracy Assessment ◽

Important Variable ◽

Field Station ◽

Near Surface ◽

Fractional Snow Cover ◽

Rgb Images ◽

Phenological Metrics

Snow cover is an important variable in both climatological and hydrological studies because of its relationship to environmental energy and mass flux. However, variability in snow cover can confound satellite-based efforts to monitor vegetation phenology. This research explores the utility of the PhenoCam Network cameras to estimate Fractional Snow Cover (FSC) in grassland. The goal is to operationalize FSC estimates from PhenoCams to inform and improve the satellite-based determination of phenological metrics. The study site is the Oakville Prairie Biological Field Station, located near Grand Forks, North Dakota. We developed a semi-automated process to estimate FSC from PhenoCam images through Python coding. Compared with previous research employing RGB images only, our use of the monochrome RGB + NIR (near-infrared) reduced pixel misclassification and increased accuracy. The results had an average RMSE of less than 8% FSC compared to visual estimates. Our pixel-based accuracy assessment showed that the overall accuracy of the images selected for validation was 92%. This is a promising outcome, although not every PhenoCam Network system has NIR capability.

Download Full-text

Spectroscopic and deep learning-based approaches to identify and quantify cerebral microhemorrhages

Scientific Reports ◽

10.1038/s41598-021-88236-1 ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Christian Crouzet ◽

Gwangjin Jeong ◽

Rachel H. Chae ◽

Krystal T. LoPresti ◽

Cody E. Dunn ◽

...

Keyword(s):

Deep Learning ◽

Prussian Blue ◽

Processing Speed ◽

Digital Pathology ◽

Ground Truth ◽

Individual Variability ◽

Rgb Images ◽

Cerebral Microhemorrhages ◽

Phasor Analysis ◽

Better Than

AbstractCerebral microhemorrhages (CMHs) are associated with cerebrovascular disease, cognitive impairment, and normal aging. One method to study CMHs is to analyze histological sections (5–40 μm) stained with Prussian blue. Currently, users manually and subjectively identify and quantify Prussian blue-stained regions of interest, which is prone to inter-individual variability and can lead to significant delays in data analysis. To improve this labor-intensive process, we developed and compared three digital pathology approaches to identify and quantify CMHs from Prussian blue-stained brain sections: (1) ratiometric analysis of RGB pixel values, (2) phasor analysis of RGB images, and (3) deep learning using a mask region-based convolutional neural network. We applied these approaches to a preclinical mouse model of inflammation-induced CMHs. One-hundred CMHs were imaged using a 20 × objective and RGB color camera. To determine the ground truth, four users independently annotated Prussian blue-labeled CMHs. The deep learning and ratiometric approaches performed better than the phasor analysis approach compared to the ground truth. The deep learning approach had the most precision of the three methods. The ratiometric approach has the most versatility and maintained accuracy, albeit with less precision. Our data suggest that implementing these methods to analyze CMH images can drastically increase the processing speed while maintaining precision and accuracy.

Download Full-text

IMG2nDSM: Height Estimation from Single Airborne RGB Images with Deep Learning

Remote Sensing ◽

10.3390/rs13122417 ◽

2021 ◽

Vol 13 (12) ◽

pp. 2417

Author(s):

Savvas Karatsiolis ◽

Andreas Kamilaris ◽

Ian Cole

Keyword(s):

Deep Learning ◽

State Of The Art ◽

Aerial Imagery ◽

Aerial Images ◽

Surface Model ◽

Large Area ◽

Digital Terrain ◽

Terrain Models ◽

Architectural Features ◽

Rgb Images

Estimating the height of buildings and vegetation in single aerial images is a challenging problem. A task-focused Deep Learning (DL) model that combines architectural features from successful DL models (U-NET and Residual Networks) and learns the mapping from a single aerial imagery to a normalized Digital Surface Model (nDSM) was proposed. The model was trained on aerial images whose corresponding DSM and Digital Terrain Models (DTM) were available and was then used to infer the nDSM of images with no elevation information. The model was evaluated with a dataset covering a large area of Manchester, UK, as well as the 2018 IEEE GRSS Data Fusion Contest LiDAR dataset. The results suggest that the proposed DL architecture is suitable for the task and surpasses other state-of-the-art DL approaches by a large margin.

Download Full-text

Leaf area index estimation using top-of-canopy airborne RGB images

International Journal of Applied Earth Observation and Geoinformation ◽

10.1016/j.jag.2020.102282 ◽

2021 ◽

Vol 96 ◽

pp. 102282

Author(s):

Rahul Raj ◽

Jeffrey P. Walker ◽

Rohit Pingale ◽

Rohit Nandan ◽

Balaji Naik ◽

...

Keyword(s):

Leaf Area Index ◽

Leaf Area ◽

Area Index ◽

Rgb Images ◽

Index Estimation

Download Full-text

Intrusion detection of railway clearance from infrared images using generative adversarial networks

Journal of Intelligent & Fuzzy Systems ◽

10.3233/jifs-192141 ◽

2020 ◽

pp. 1-13

Author(s):

Yundong Li ◽

Yi Liu ◽

Han Dong ◽

Wei Hu ◽

Chen Lin

Keyword(s):

Intrusion Detection ◽

Synthetic Data ◽

Generative Adversarial Networks ◽

Generation Model ◽

Single Shot ◽

Data Generation ◽

Infrared Images ◽

Adversarial Networks ◽

Training Samples ◽

Rgb Images

The intrusion detection of railway clearance is crucial for avoiding railway accidents caused by the invasion of abnormal objects, such as pedestrians, falling rocks, and animals. However, detecting intrusions using deep learning methods from infrared images captured at night remains a challenging task because of the lack of sufficient training samples. To address this issue, a transfer strategy that migrates daytime RGB images to the nighttime style of infrared images is proposed in this study. The proposed method consists of two stages. In the first stage, a data generation model is trained on the basis of generative adversarial networks using RGB images and a small number of infrared images, and then, synthetic samples are generated using a well-trained model. In the second stage, a single shot multibox detector (SSD) model is trained using synthetic data and utilized to detect abnormal objects from infrared images at nighttime. To validate the effectiveness of the proposed method, two groups of experiments, namely, railway and non-railway scenes, are conducted. Experimental results demonstrate the effectiveness of the proposed method, and an improvement of 17.8% is achieved for object detection at nighttime.

Download Full-text

Using UAV Imagery to Detect and Map Woody Species Encroachment in a Subalpine Grassland: Advantages and Limits

Remote Sensing ◽

10.3390/rs13071239 ◽

2021 ◽

Vol 13 (7) ◽

pp. 1239

Author(s):

Ludovica Oddi ◽

Edoardo Cremonese ◽

Lorenzo Ascari ◽

Gianluca Filippa ◽

Marta Galvagno ◽

...

Keyword(s):

Reference Data ◽

Woody Species ◽

Accurate Method ◽

Machine Learning Algorithms ◽

Italian Alps ◽

Photo Interpretation ◽

Tree Detection ◽

Grassland Ecosystems ◽

Object Based ◽

Rgb Images

Woody species encroachment on grassland ecosystems is occurring worldwide with both negative and positive consequences for biodiversity conservation and ecosystem services. Remote sensing and image analysis represent useful tools for the monitoring of this process. In this paper, we aimed at evaluating quantitatively the potential of using high-resolution UAV imagery to monitor the encroachment process during its early development and at comparing the performance of manual and semi-automatic classification methods. The RGB images of an abandoned subalpine grassland on the Western Italian Alps were acquired by drone and then classified through manual photo-interpretation, with both pixel- and object-based semi-automatic models, using machine-learning algorithms. The classification techniques were applied at different resolution levels and tested for their accuracy against reference data including measurements of tree dimensions collected in the field. Results showed that the most accurate method was the photo-interpretation (≈99%), followed by the pixel-based approach (≈86%) that was faster than the manual technique and more accurate than the object-based one (≈78%). The dimensional threshold for juvenile tree detection was lower for the photo-interpretation but comparable to the pixel-based one. Therefore, for the encroachment mapping at its early stages, the pixel-based approach proved to be a promising and pragmatic choice.

Download Full-text

HRDepthNet: Depth Image-Based Marker-Less Tracking of Body Joints

Sensors ◽

10.3390/s21041356 ◽

2021 ◽

Vol 21 (4) ◽

pp. 1356

Author(s):

Linda Christin Büker ◽

Finnja Zuber ◽

Andreas Hein ◽

Sebastian Fudickar

Keyword(s):

Color Images ◽

Depth Image ◽

Accuracy Evaluation ◽

Timed Up And Go ◽

Position Errors ◽

Depth Images ◽

Upper And Lower Extremities ◽

Rgb Images ◽

Human Joints ◽

Body Joints

With approaches for the detection of joint positions in color images such as HRNet and OpenPose being available, consideration of corresponding approaches for depth images is limited even though depth images have several advantages over color images like robustness to light variation or color- and texture invariance. Correspondingly, we introduce High- Resolution Depth Net (HRDepthNet)—a machine learning driven approach to detect human joints (body, head, and upper and lower extremities) in purely depth images. HRDepthNet retrains the original HRNet for depth images. Therefore, a dataset is created holding depth (and RGB) images recorded with subjects conducting the timed up and go test—an established geriatric assessment. The images were manually annotated RGB images. The training and evaluation were conducted with this dataset. For accuracy evaluation, detection of body joints was evaluated via COCO’s evaluation metrics and indicated that the resulting depth image-based model achieved better results than the HRNet trained and applied on corresponding RGB images. An additional evaluation of the position errors showed a median deviation of 1.619 cm (x-axis), 2.342 cm (y-axis) and 2.4 cm (z-axis).

Download Full-text