scholarly journals ACF Based Region Proposal Extraction for YOLOv3 Network Towards High-Performance Cyclist Detection in High Resolution Images

Sensors ◽  
2019 ◽  
Vol 19 (12) ◽  
pp. 2671 ◽  
Author(s):  
Chunsheng Liu ◽  
Yu Guo ◽  
Shuang Li ◽  
Faliang Chang
Keyword(s):  
High Resolution ◽  
High Precision ◽  
Extraction Method ◽  
High Performance ◽  
Detection Methods ◽  
Average Precision ◽  
Deep Network ◽  
High Resolution Images ◽  
Bounding Boxes ◽  
Detection And Localization

You Only Look Once (YOLO) deep network can detect objects quickly with high precision and has been successfully applied in many detection problems. The main shortcoming of YOLO network is that YOLO network usually cannot achieve high precision when dealing with small-size object detection in high resolution images. To overcome this problem, we propose an effective region proposal extraction method for YOLO network to constitute an entire detection structure named ACF-PR-YOLO, and take the cyclist detection problem to show our methods. Instead of directly using the generated region proposals for classification or regression like most region proposal methods do, we generate large-size potential regions containing objects for the following deep network. The proposed ACF-PR-YOLO structure includes three main parts. Firstly, a region proposal extraction method based on aggregated channel feature (ACF) is proposed, called ACF based region proposal (ACF-PR) method. In ACF-PR, ACF is firstly utilized to fast extract candidates and then a bounding boxes merging and extending method is designed to merge the bounding boxes into correct region proposals for the following YOLO net. Secondly, we design suitable YOLO net for fine detection in the region proposals generated by ACF-PR. Lastly, we design a post-processing step, in which the results of YOLO net are mapped into the original image outputting the detection and localization results. Experiments performed on the Tsinghua-Daimler Cyclist Benchmark with high resolution images and complex scenes show that the proposed method outperforms the other tested representative detection methods in average precision, and that it outperforms YOLOv3 by 13.69 % average precision and outperforms SSD by 25.27 % average precision.

High-resolution LCOS microdisplay with sub-kHz frame rate for high performance, high precision 3D sensor

2017 ◽  
Author(s):  
Grigory Lazarev ◽  
Stefanie Bonifer ◽  
Philip Engel ◽  
Daniel Höhne ◽  
Gunther Notni
Keyword(s):  
High Resolution ◽  
High Precision ◽  
High Performance ◽  
Frame Rate

scholarly journals Weighted Ensemble Object Detection with Optimized Coefficients for Remote Sensing Images

2020 ◽  
Vol 9 (6) ◽  
pp. 370
Author(s):  
Atakan Körez ◽  
Necaattin Barışçı ◽  
Aydın Çetin ◽  
Uçman Ergün
Keyword(s):  
Remote Sensing ◽  
High Resolution ◽  
Object Detection ◽  
Mean Average Precision ◽  
Detection Methods ◽  
Remote Sensing Images ◽  
Average Precision ◽  
Proposed Model ◽  
Detection Of Objects ◽  
Very High

The detection of objects in very high-resolution (VHR) remote sensing images has become increasingly popular with the enhancement of remote sensing technologies. High-resolution images from aircrafts or satellites contain highly detailed and mixed backgrounds that decrease the success of object detection in remote sensing images. In this study, a model that performs weighted ensemble object detection using optimized coefficients is proposed. This model uses the outputs of three different object detection models trained on the same dataset. The model’s structure takes two or more object detection methods as its input and provides an output with an optimized coefficient-weighted ensemble. The Northwestern Polytechnical University Very High Resolution 10 (NWPU-VHR10) and Remote Sensing Object Detection (RSOD) datasets were used to measure the object detection success of the proposed model. Our experiments reveal that the proposed model improved the Mean Average Precision (mAP) performance by 0.78%–16.5% compared to stand-alone models and presents better mean average precision than other state-of-the-art methods (3.55% higher on the NWPU-VHR-10 dataset and 1.49% higher when using the RSOD dataset).

scholarly journals A Fast Steering Mirror Using a Compact Magnetic Suspension and Voice Coil Motors for Observation Satellites

Electronics ◽  
2020 ◽  
Vol 9 (12) ◽  
pp. 1997
Author(s):  
Tadahiko Shinshi ◽  
Daisuke Shimizu ◽  
Kazuhide Kodeki ◽  
Kazuhiko Fukushima
Keyword(s):  
High Resolution ◽  
Active Control ◽  
Long Range ◽  
High Precision ◽  
Friction And Wear ◽  
Large Scale ◽  
Large Diameter ◽  
Magnetic Suspension ◽  
High Resolution Images ◽  
Long Stroke

Fast steering mirrors (FSMs) are used to correct images observed by satellites. FSMs need to have large apertures and realize high precision and the positioning of the mirror in the tip-tilt and axial directions needs to be highly precise and highly responsive in order to capture large-scale, high-resolution images. An FSM with a large-diameter mirror supported by a compact magnetic suspension and driven by long-stroke voice coil motors (VCMs) is proposed in this paper. The magnetic suspension and VCM actuators enable the mirror to be highly responsive and to have long-range movement in the tip-tilt and axial directions without friction and wear. The magnetic suspension is a hybrid that has active control in the lateral directions and passive support in the tip-tilt and axial directions. An experimental FSM with an 80 mm diameter dummy mirror was fabricated and tested. The mirror’s driving ranges in the tip-tilt and axial directions were ±20 mrad and ±500 μm, respectively. Furthermore, the servo bandwidths in the tip-tilt and axial directions were more than 1 kHz and 200 Hz, respectively.

scholarly journals VEHICLE DETECTION IN HIGH RESOLUTION IMAGE BASED ON DEEP LEARNING

2020 ◽  
Vol XLIII-B3-2020 ◽  
pp. 49-54
Author(s):  
H. Gao ◽  
X. Li
Keyword(s):  
High Resolution ◽  
Object Detection ◽  
Feature Fusion ◽  
Single Shot ◽  
Feature Maps ◽  
Average Precision ◽  
Speed Up ◽  
High Resolution Images ◽  
Small Targets ◽  
Fusion Feature

Abstract. Despite its high accuracy and fast speed in object detection, Single Shot Multi-Box Detector (SSD) tends to get undesirable results especially for small targets such as vehicles on high-resolution images. In this paper, we propose a new convolutional neural network based on SSD to detect vehicles on high-resolution images. In the proposed framework, the feature fusion module and detection module are incorporated. In the feature fusion module, feature maps of different scales are integrated into a fusion feature for object detection, which could improve the accuracy effectively. Besides, to prevent the network from overfitting and speed up the training, the batch normalization layer is embedded between the detection layers in the detection module. Some ablation experiments provide strong evidence for the effectiveness of these above structures. On the UCAS-High Resolution Aerial Object Detection Dataset, our network has the ability to achieve the 0.904 AP (average precision) with 0.094 AP higher than SSD512 but similar speed to it.

scholarly journals Qualitative Comparison of 2D and 3D Atmospheric Corrosion Detection Methods

Materials ◽  
2021 ◽  
Vol 14 (13) ◽  
pp. 3621
Author(s):  
Thomas De Kerf ◽  
Navid Hasheminejad ◽  
Johan Blom ◽  
Steve Vanlanduit
Keyword(s):  
High Resolution ◽  
Atmospheric Corrosion ◽  
Laser Scanning ◽  
Added Value ◽  
Qualitative Assessment ◽  
Detection Methods ◽  
Confocal Laser ◽  
Significant Difference ◽  
Segmentation Algorithms ◽  
High Resolution Images

In this article, we report the use of a Confocal Laser Scanning Microscope (CLSM) to apply a qualitative assessment of atmospheric corrosion on steel samples. From the CLSM, we obtain high-resolution images, together with a 3D heightmap. The performance of four different segmentation algorithms that use the high-resolution images as input is qualitatively assessed and discussed. A novel 3D segmentation algorithm based on the shape index is presented and compared to the 2D segmentation algorithms. From this analysis, we conclude that there is a significant difference in performance between the 2D segmentation algorithms and that the 3D method can be an added value to the detection of corrosion.

FeXIV Line Emission Polarization of the July 11, 1991 Solar Corona

1994 ◽  
Vol 144 ◽  
pp. 541-547
Author(s):  
J. Sýkora ◽  
J. Rybák ◽  
P. Ambrož
Keyword(s):  
High Resolution ◽  
Solar Corona ◽  
Emission Line ◽  
Solar Eclipse ◽  
White Light ◽  
Preliminary Analysis ◽  
Line Emission ◽  
Total Solar Eclipse ◽  
Degree Of Polarization ◽  
High Resolution Images

AbstractHigh resolution images, obtained during July 11, 1991 total solar eclipse, allowed us to estimate the degree of solar corona polarization in the light of FeXIV 530.3 nm emission line and in the white light, as well. Very preliminary analysis reveals remarkable differences in the degree of polarization for both sets of data, particularly as for level of polarization and its distribution around the Sun’s limb.

Remarks on the application of backscattered electron imaging (BEI) to the scanning electron microscopy (SEM) of biological structures

1983 ◽  
Vol 41 ◽  
pp. 484-487
Author(s):  
Etienne de Harven
Keyword(s):  
High Resolution ◽  
Incident Beam ◽  
Spot Size ◽  
Primary Electron ◽  
Critical Point Drying ◽  
Cell Shapes ◽  
High Resolution Images ◽  
Backscattered Electron ◽  
Electron Imaging ◽  
Scanning Electron

Biological ultrastructures have been extensively studied with the scanning electron microscope (SEM) for the past 12 years mainly because this instrument offers accurate and reproducible high resolution images of cell shapes, provided the cells are dried in ways which will spare them the damage which would be caused by air drying. This can be achieved by several techniques among which the critical point drying technique of T. Anderson has been, by far, the most reproducibly successful. Many biologists, however, have been interpreting SEM micrographs in terms of an exclusive secondary electron imaging (SEI) process in which the resolution is primarily limited by the spot size of the primary incident beam. in fact, this is not the case since it appears that high resolution, even on uncoated samples, is probably compromised by the emission of secondary electrons of much more complex origin.When an incident primary electron beam interacts with the surface of most biological samples, a large percentage of the electrons penetrate below the surface of the exposed cells.

Field Emission SEM Equipped With Noise Compensator

1973 ◽  
Vol 31 ◽  
pp. 302-303
Author(s):  
S. Saito ◽  
H. Todokoro ◽  
S. Nomura ◽  
T. Komoda
Keyword(s):  
Electron Microscope ◽  
High Resolution ◽  
Scanning Electron Microscope ◽  
Field Emission ◽  
Low Contrast ◽  
Probe Current ◽  
High Resolution Images ◽  
Scanning Electron

Field emission scanning electron microscope (FESEM) features extremely high resolution images, and offers many valuable information. But, for a specimen which gives low contrast images, lateral stripes appear in images. These stripes are resulted from signal fluctuations caused by probe current noises. In order to obtain good images without stripes, the fluctuations should be less than 1%, especially for low contrast images. For this purpose, the authors realized a noise compensator, and applied this to the FESEM.Fig. 1 shows an outline of FESEM equipped with a noise compensator. Two apertures are provided gust under the field emission gun.

Low-Loss Images in a Stem/Tem Microscope

1976 ◽  
Vol 34 ◽  
pp. 496-497 ◽  
Author(s):  
David C. Joy ◽  
Dennis M. Maher
Keyword(s):  
High Resolution ◽  
Surface Topography ◽  
Beam Direction ◽  
Low Loss ◽  
Specimen Holder ◽  
Glancing Angle ◽  
High Resolution Images ◽  
Set Up ◽  
Conventional Manner ◽  
Objective Type

High-resolution images of the surface topography of solid specimens can be obtained using the low-loss technique of Wells. If the specimen is placed inside a lens of the condenser/objective type, then it has been shown that the lens itself can be used to collect and filter the low-loss electrons. Since the probeforming lenses in TEM instruments fitted with scanning attachments are of this type, low-loss imaging should be possible.High-resolution, low-loss images have been obtained in a JEOL JEM 100B fitted with a scanning attachment and a thermal, fieldemission gun. No modifications were made to the instrument, but a wedge-shaped, specimen holder was made to fit the side-entry, goniometer stage. Thus the specimen is oriented initially at a glancing angle of about 30° to the beam direction. The instrument is set up in the conventional manner for STEM operation with all the lenses, including the projector, excited.

Effect of strain on ADF-STEM high-resolution images

1991 ◽  
Vol 49 ◽  
pp. 666-667
Author(s):  
M. Kelly ◽  
D.M. Bird
Keyword(s):  
High Resolution ◽  
Strong Influence ◽  
Intensity Variation ◽  
Dark Field ◽  
Atomic Resolution ◽  
Strain Fields ◽  
High Resolution Image ◽  
Annular Dark Field ◽  
High Resolution Images ◽  
Interesting Alternative

It is well known that strain fields can have a strong influence on the details of HREM images. This, for example, can cause problems in the analysis of edge-on interfaces between lattice mismatched materials. An interesting alternative to conventional HREM imaging has recently been advanced by Pennycook and co-workers where the intensity variation in the annular dark field (ADF) detector is monitored as a STEM probe is scanned across the specimen. It is believed that the observed atomic-resolution contrast is correlated with the intensity of the STEM probe at the atomic sites and the way in which this varies as the probe moves from cell to cell. As well as providing a directly interpretable high-resolution image, there are reasons for believing that ADF-STEM images may be less suseptible to strain than conventional HREM. This is because HREM images arise from the interference of several diffracted beams, each of which is governed by all the excited Bloch waves in the crystal.

Sign in / Sign up

Export Citation Format

Share Document