scholarly journals The effect of image resolution in the human presence detection: A case study on real-world image data

2020 ◽  
Vol 8 (1) ◽  
pp. 53-62
Author(s):  
Alexander Leipnitz ◽  
Tilo Strutz ◽  
Oliver Jokisch
Keyword(s):  
High Resolution ◽  
Object Detection ◽  
Relative Size ◽  
Image Data ◽  
Image Resolution ◽  
Human Detection ◽  
Security Requirements ◽  
Long Distance ◽  
Detection Rates ◽  
Input Layer

The automated operation of robots and flying drones is coupled to high security requirements with respect to humans and environment. Sometimes, persons have to be detected from a long distance or high altitude to allow the autonomous system an adequate and timely response. State-of-the-art Convolutional Neural Networks (CNNs) enable high object detection rates for different image data but only within their respective training, validation and test datasets. Recent studies show the limited generalization ability of CNNs for unknown data, even with merely small image changes. A typical source of such problems is the varying resolution of input images and the inevitable scaling of them to match the input-layer size of the network model. While modern cameras are able to capture high-resolution images of humans also from a longer distance, the practical input-layer sizes of networks are comparably small. Hence, we investigate the reliability of a network architecture for human detection with respect to such input-scaling effects. The popular VisDrone dataset with its varying image resolution and many relatively small depictions of humans is surveyed as well as the high-resolution AgriDrone image data from an agricultural context. Our results show that the object detection rate depends on the image scaling factor as well as on the relative size of persons. An enlarged input-layer size of the network can only partially contribute to counteract the observed effects. In addition, the detection algorithm becomes computationally more expensive by the increased effort.

scholarly journals TasselNetV2+: A Fast Implementation for High-Throughput Plant Counting From High-Resolution RGB Imagery

2020 ◽  
Vol 11 ◽  
Author(s):  
Hao Lu ◽  
Zhiguo Cao
Keyword(s):  
High Resolution ◽  
Object Detection ◽  
High Throughput ◽  
Graphics Processing Units ◽  
State Of The Art ◽  
Image Resolution ◽  
Plant Phenotyping ◽  
Art Object ◽  
Bounding Boxes ◽  
Computational Bottleneck

Plant counting runs through almost every stage of agricultural production from seed breeding, germination, cultivation, fertilization, pollination to yield estimation, and harvesting. With the prevalence of digital cameras, graphics processing units and deep learning-based computer vision technology, plant counting has gradually shifted from traditional manual observation to vision-based automated solutions. One of popular solutions is a state-of-the-art object detection technique called Faster R-CNN where plant counts can be estimated from the number of bounding boxes detected. It has become a standard configuration for many plant counting systems in plant phenotyping. Faster R-CNN, however, is expensive in computation, particularly when dealing with high-resolution images. Unfortunately high-resolution imagery is frequently used in modern plant phenotyping platforms such as unmanned aerial vehicles, engendering inefficient image analysis. Such inefficiency largely limits the throughput of a phenotyping system. The goal of this work hence is to provide an effective and efficient tool for high-throughput plant counting from high-resolution RGB imagery. In contrast to conventional object detection, we encourage another promising paradigm termed object counting where plant counts are directly regressed from images, without detecting bounding boxes. In this work, by profiling the computational bottleneck, we implement a fast version of a state-of-the-art plant counting model TasselNetV2 with several minor yet effective modifications. We also provide insights why these modifications make sense. This fast version, TasselNetV2+, runs an order of magnitude faster than TasselNetV2, achieving around 30 fps on image resolution of 1980 × 1080, while it still retains the same level of counting accuracy. We validate its effectiveness on three plant counting tasks, including wheat ears counting, maize tassels counting, and sorghum heads counting. To encourage the use of this tool, our implementation has been made available online at https://tinyurl.com/TasselNetV2plus.

THE RECONSTRUCTION OF SATELLITE IMAGES BASED ON FRACTAL INTERPOLATION

Fractals ◽  
2011 ◽  
Vol 19 (03) ◽  
pp. 347-354 ◽  
Author(s):  
CHING-JU CHEN ◽  
SHU-CHEN CHENG ◽  
Y. M. HUANG
Keyword(s):  
High Resolution ◽  
Satellite Images ◽  
Satellite Image ◽  
Image Data ◽  
Image Resolution ◽  
Source Image ◽  
Fractal Interpolation ◽  
Low Resolution ◽  
Resolution Image ◽  
High Resolution Image

This study discussed the application of a fractal interpolation method in satellite image data reconstruction. It used low-resolution images as the source data for fractal interpolation reconstruction. Using this approach, a high-resolution image can be reconstructed when there is only a low-resolution source image available. The results showed that the high-resolution image data from fractal interpolation can effectively enhance the sharpness of the border contours. Implementing fractal interpolation on an insufficient image resolution image can avoid jagged edges and mosaic when enlarging the image, as well as improve the visibility of object features in the region of interest. The proposed approach can thus be a useful tool in land classification by satellite images.

scholarly journals Object detection in high resolution images based on multiscale and block processing

Informatics ◽  
2020 ◽  
Vol 17 (2) ◽  
pp. 7-16
Author(s):  
R. P. Bohush ◽  
I. Yu. Zakharava ◽  
S. V. Ablameyko
Keyword(s):  
Neural Network ◽  
High Resolution ◽  
Object Detection ◽  
Convolutional Neural Network ◽  
Image Representation ◽  
Input Image ◽  
Image Resolution ◽  
Detection Accuracy ◽  
Block Processing ◽  
High Resolution Images

In the paper the algorithm for object detection in high resolution images is proposed. The approach uses multiscale image representation followed by block processing with the overlapping value. For each block the object detection with convolutional neural network was performed. Number of pyramid layers is limited by the Convolutional Neural Network layer size and input image resolution. Overlapping blocks splitting to improve the classification and detection accuracy is performed on each layer of pyramid except the highest one. Detected areas are merged into one if they have high overlapping value and the same class. Experimental results for the algorithm are presented in the paper.

scholarly journals Instance Segmentation for Governmental Inspection of Small Touristic Infrastructure in Beach Zones Using Multispectral High-Resolution WorldView-3 Imagery

2021 ◽  
Vol 10 (12) ◽  
pp. 813
Author(s):  
Osmar Luiz Ferreira de Carvalho ◽  
Rebeca dos Santos de Moura ◽  
Anesmar Olino de Albuquerque ◽  
Pablo Pozzobon de Bem ◽  
Rubens de Castro Pereira ◽  
...  
Keyword(s):  
High Resolution ◽  
Object Detection ◽  
Sliding Window ◽  
Coastal Areas ◽  
Image Resolution ◽  
Small Object ◽  
Original Image ◽  
Individual Object ◽  
High Resolution Images ◽  
Instance Segmentation

Misappropriation of public lands is an ongoing government concern. In Brazil, the beach zone is public property, but many private establishments use it for economic purposes, requiring constant inspection. Among the undue targets, the individual mapping of straw beach umbrellas (SBUs) attached to the sand is a great challenge due to their small size, high presence, and agglutinated appearance. This study aims to automatically detect and count SBUs on public beaches using high-resolution images and instance segmentation, obtaining pixel-wise semantic information and individual object detection. This study is the first instance segmentation application on coastal areas and the first using WorldView-3 (WV-3) images. We used the Mask-RCNN with some modifications: (a) multispectral input for the WorldView3 imagery (eight channels), (b) improved the sliding window algorithm for large image classification, and (c) comparison of different image resizing ratios to improve small object detection since the SBUs are small objects (<322 pixels) even using high-resolution images (31 cm). The accuracy analysis used standard COCO metrics considering the original image and three scale ratios (2×, 4×, and 8× resolution increase). The average precision (AP) results increased proportionally to the image resolution: 30.49% (original image), 48.24% (2×), 53.45% (4×), and 58.11% (8×). The 8× model presented 94% AP50, classifying nearly all SBUs correctly. Moreover, the improved sliding window approach enables the classification of large areas providing automatic counting and estimating the size of the objects, proving to be effective for inspecting large coastal areas and providing insightful information for public managers. This remote sensing application impacts the inspection cost, tribute, and environmental conditions.

Towards 1-Ångstrom-resolution STEM

1993 ◽  
Vol 51 ◽  
pp. 996-997
Author(s):  
H.S. von Harrach ◽  
D.E. Jesson ◽  
S.J. Pennycook
Keyword(s):  
High Resolution ◽  
Field Emission ◽  
Phase Contrast ◽  
Spherical Aberration ◽  
A Priori ◽  
Dark Field ◽  
Image Resolution ◽  
Objective Lens ◽  
Annular Dark Field ◽  
First Results

Phase contrast TEM has been the leading technique for high resolution imaging of materials for many years, whilst STEM has been the principal method for high-resolution microanalysis. However, it was demonstrated many years ago that low angle dark-field STEM imaging is a priori capable of almost 50% higher point resolution than coherent bright-field imaging (i.e. phase contrast TEM or STEM). This advantage was not exploited until Pennycook developed the high-angle annular dark-field (ADF) technique which can provide an incoherent image showing both high image resolution and atomic number contrast.This paper describes the design and first results of a 300kV field-emission STEM (VG Microscopes HB603U) which has improved ADF STEM image resolution towards the 1 angstrom target. The instrument uses a cold field-emission gun, generating a 300 kV beam of up to 1 μA from an 11-stage accelerator. The beam is focussed on to the specimen by two condensers and a condenser-objective lens with a spherical aberration coefficient of 1.0 mm.

scholarly journals U-Infuse: Democratization of Customizable Deep Learning for Object Detection

Sensors ◽  
2021 ◽  
Vol 21 (8) ◽  
pp. 2611
Author(s):  
Andrew Shepley ◽  
Greg Falzon ◽  
Christopher Lawson ◽  
Paul Meek ◽  
Paul Kwan
Keyword(s):  
Deep Learning ◽  
Intellectual Property ◽  
Object Detection ◽  
Image Data ◽  
Learning Technologies ◽  
Training Data ◽  
Learning Models ◽  
Ecological Data ◽  
Single Class ◽  
Large Numbers

Image data is one of the primary sources of ecological data used in biodiversity conservation and management worldwide. However, classifying and interpreting large numbers of images is time and resource expensive, particularly in the context of camera trapping. Deep learning models have been used to achieve this task but are often not suited to specific applications due to their inability to generalise to new environments and inconsistent performance. Models need to be developed for specific species cohorts and environments, but the technical skills required to achieve this are a key barrier to the accessibility of this technology to ecologists. Thus, there is a strong need to democratize access to deep learning technologies by providing an easy-to-use software application allowing non-technical users to train custom object detectors. U-Infuse addresses this issue by providing ecologists with the ability to train customised models using publicly available images and/or their own images without specific technical expertise. Auto-annotation and annotation editing functionalities minimize the constraints of manually annotating and pre-processing large numbers of images. U-Infuse is a free and open-source software solution that supports both multiclass and single class training and object detection, allowing ecologists to access deep learning technologies usually only available to computer scientists, on their own device, customised for their application, without sharing intellectual property or sensitive data. It provides ecological practitioners with the ability to (i) easily achieve object detection within a user-friendly GUI, generating a species distribution report, and other useful statistics, (ii) custom train deep learning models using publicly available and custom training data, (iii) achieve supervised auto-annotation of images for further training, with the benefit of editing annotations to ensure quality datasets. Broad adoption of U-Infuse by ecological practitioners will improve ecological image analysis and processing by allowing significantly more image data to be processed with minimal expenditure of time and resources, particularly for camera trap images. Ease of training and use of transfer learning means domain-specific models can be trained rapidly, and frequently updated without the need for computer science expertise, or data sharing, protecting intellectual property and privacy.

scholarly journals Archaeological Surveying of Subarctic and Arctic Landscapes: Comparing the Performance of Airborne Laser Scanning and Remote Sensing Image Data

2021 ◽  
Vol 13 (4) ◽  
pp. 1917
Author(s):  
Alma Elizabeth Thuestad ◽  
Ole Risbøl ◽  
Jan Ingolf Kleppe ◽  
Stine Barlindhaug ◽  
Elin Rose Myrvoll
Keyword(s):  
Remote Sensing ◽  
Laser Scanning ◽  
Digital Terrain Model ◽  
Image Data ◽  
Remote Sensing Image ◽  
Airborne Laser Scanning ◽  
Aerial Images ◽  
Detection Rates ◽  
Airborne Laser ◽  
Pros And Cons

What can remote sensing contribute to archaeological surveying in subarctic and arctic landscapes? The pros and cons of remote sensing data vary as do areas of utilization and methodological approaches. We assessed the applicability of remote sensing for archaeological surveying of northern landscapes using airborne laser scanning (LiDAR) and satellite and aerial images to map archaeological features as a basis for (a) assessing the pros and cons of the different approaches and (b) assessing the potential detection rate of remote sensing. Interpretation of images and a LiDAR-based bare-earth digital terrain model (DTM) was based on visual analyses aided by processing and visualizing techniques. 368 features were identified in the aerial images, 437 in the satellite images and 1186 in the DTM. LiDAR yielded the better result, especially for hunting pits. Image data proved suitable for dwellings and settlement sites. Feature characteristics proved a key factor for detectability, both in LiDAR and image data. This study has shown that LiDAR and remote sensing image data are highly applicable for archaeological surveying in northern landscapes. It showed that a multi-sensor approach contributes to high detection rates. Our results have improved the inventory of archaeological sites in a non-destructive and minimally invasive manner.

Accelerating real‐time object detection in high‐resolution video surveillance

2021 ◽  
Author(s):  
Yuefeng Wang ◽  
Kuang Mao ◽  
Tong Chen ◽  
Yanglong Yin ◽  
Shuibing He ◽  
...  
Keyword(s):  
High Resolution ◽  
Object Detection ◽  
Real Time ◽  
Video Surveillance
Sign in / Sign up

Export Citation Format

Share Document