Distance Estimation in Thermal Cameras Using Multi-task Cascaded Convolutional Neural Network

2021 ◽  
pp. 1-1
Author(s):  
Ej Miguel Francisco Caliwag ◽  
Angela Caliwag ◽  
Bong-ki Baek ◽  
Yongrae Jo ◽  
Hae Chung ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Distance Estimation ◽  
Thermal Cameras

scholarly journals The Design of Preventive Automated Driving Systems Based on Convolutional Neural Network

Electronics ◽  
2021 ◽  
Vol 10 (14) ◽  
pp. 1737
Author(s):  
Wooseop Lee ◽  
Min-Hee Kang ◽  
Jaein Song ◽  
Keeyeon Hwang
Keyword(s):  
Neural Network ◽  
Object Detection ◽  
Convolutional Neural Network ◽  
Processing Speed ◽  
Model Comparison ◽  
Distance Estimation ◽  
Visual Object ◽  
Suitable Model ◽  
Automated Vehicles ◽  
Automated Driving

As automated vehicles have been considered one of the important trends in intelligent transportation systems, various research is being conducted to enhance their safety. In particular, the importance of technologies for the design of preventive automated driving systems, such as detection of surrounding objects and estimation of distance between vehicles. Object detection is mainly performed through cameras and LiDAR, but due to the cost and limits of LiDAR’s recognition distance, the need to improve Camera recognition technique, which is relatively convenient for commercialization, is increasing. This study learned convolutional neural network (CNN)-based faster regions with CNN (Faster R-CNN) and You Only Look Once (YOLO) V2 to improve the recognition techniques of vehicle-mounted monocular cameras for the design of preventive automated driving systems, recognizing surrounding vehicles in black box highway driving videos and estimating distances from surrounding vehicles through more suitable models for automated driving systems. Moreover, we learned the PASCAL visual object classes (VOC) dataset for model comparison. Faster R-CNN showed similar accuracy, with a mean average precision (mAP) of 76.4 to YOLO with a mAP of 78.6, but with a Frame Per Second (FPS) of 5, showing slower processing speed than YOLO V2 with an FPS of 40, and a Faster R-CNN, which we had difficulty detecting. As a result, YOLO V2, which shows better performance in accuracy and processing speed, was determined to be a more suitable model for automated driving systems, further progressing in estimating the distance between vehicles. For distance estimation, we conducted coordinate value conversion through camera calibration and perspective transform, set the threshold to 0.7, and performed object detection and distance estimation, showing more than 80% accuracy for near-distance vehicles. Through this study, it is believed that it will be able to help prevent accidents in automated vehicles, and it is expected that additional research will provide various accident prevention alternatives such as calculating and securing appropriate safety distances, depending on the vehicle types.

Distance Estimation Based on Deep Convolutional Neural Network Using Ultra-Wideband Signals

2020 ◽  
Vol 17 (7) ◽  
pp. 3212-3217
Author(s):  
Gyeong-Mo Nam ◽  
Eui-Rim Jeong
Keyword(s):  
Neural Network ◽  
Computer Simulation ◽  
Convolutional Neural Network ◽  
Distance Estimation ◽  
High Accuracy ◽  
Deep Convolutional Neural Network ◽  
Ultra Wideband ◽  
Long Distance ◽  
Location Services ◽  
Distance Estimator

Recently, high accuracy localization technique is required to provide indoor location services. The purpose of this paper is to propose a distance estimation technique based on deep convolutional neural network (DCNN) for indoor environments. Among distance estimation techniques based on wireless communication signals, the use of ultra-wideband (UWB) signals has the advantage of high accuracy in the time domain. The proposed distance estimation method uses UWB signals and proposes a new DCNN-based distance estimator. The superiority of the proposed method is confirmed through computer simulation. Widely used conventional distance estimators are based on the power threshold. The threshold is determined by signal to noise ratio (SNR) of the received signal. The arrival time of the received signal that exceeds the threshold is considered as the time-of-arrival (ToA) and the distance between transmitter and receiver is obtained from the ToA. On the other hand, the proposed distance estimator requires only the received signal without SNR estimation, which make the proposed technique simpler to implement. According to computer simulation, the conventional method is highly sensitive to SNR and distance. In contrast, the proposed method shows less than 2 m root mean square error (RMSE) performance in a wide range of SNR and the RMSE performance is not degraded in long distances. The proposed distance estimator shows excellent distance estimation performance at low SNR and long distance, so it can be applied to indoor localization system of large indoor space and can be used for precise location service.

CONVOLUTIONAL NEURAL NETWORK BASED ALGORITHM FOR CECUM ACHIEVEMENT CONFIRMATION

2020 ◽  
Author(s):  
S Kashin ◽  
D Zavyalov ◽  
A Rusakov ◽  
V Khryashchev ◽  
A Lebedev
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network

Non-Blind Image Deconvolution Based on “Ringing” Removal Using Convolutional Neural Network

2020 ◽  
Vol 2020 (10) ◽  
pp. 181-1-181-7
Author(s):  
Takahiro Kudo ◽  
Takanori Fujisawa ◽  
Takuro Yamaguchi ◽  
Masaaki Ikehara
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Network Architecture ◽  
Large Scale ◽  
Blind Deconvolution ◽  
Training Dataset ◽  
Image Deconvolution ◽  
Classic Problem ◽  
Key Points ◽  
Blind Image

Image deconvolution has been an important issue recently. It has two kinds of approaches: non-blind and blind. Non-blind deconvolution is a classic problem of image deblurring, which assumes that the PSF is known and does not change universally in space. Recently, Convolutional Neural Network (CNN) has been used for non-blind deconvolution. Though CNNs can deal with complex changes for unknown images, some CNN-based conventional methods can only handle small PSFs and does not consider the use of large PSFs in the real world. In this paper we propose a non-blind deconvolution framework based on a CNN that can remove large scale ringing in a deblurred image. Our method has three key points. The first is that our network architecture is able to preserve both large and small features in the image. The second is that the training dataset is created to preserve the details. The third is that we extend the images to minimize the effects of large ringing on the image borders. In our experiments, we used three kinds of large PSFs and were able to observe high-precision results from our method both quantitatively and qualitatively.

Sign in / Sign up

Export Citation Format

Share Document