scholarly journals Application of Deep Learning and Unmanned Aerial Vehicle on Building Maintenance

2021 ◽  
Vol 2021 ◽  
pp. 1-12
Author(s):  
Ren-Yi Kung ◽  
Nai-Hsin Pan ◽  
Charles C.N. Wang ◽  
Pin-Chan Lee
Keyword(s):  
Deep Learning ◽  
Detection Efficiency ◽  
Real Life ◽  
Object Localization ◽  
Safety Hazard ◽  
External Wall ◽  
Building Maintenance ◽  
Aerial Vehicle ◽  
Detection And Localization ◽  
Activation Mapping

Several natural and human factors are responsible for the defacement of the external walls and tiles of buildings, and the related deterioration can be a public safety hazard. Therefore, active building maintenance and repair processes are essential for ensuring building sustainability. However, conventional inspection methods are time-, cost-, and labor-intensive processes. Therefore, herein, this study proposes a convolutional neural network (CNN) model for image-based automated detection and localization of key building defects (efflorescence, spalling, cracking, and defacement). Based on a pretrained CNN VGG-16 classifier, this model applies class activation mapping for object localization. After identifying its limitations in real-life applications, this study determined the model’s robustness and ability to accurately detect and localize defects in the external wall tiles of buildings. For real-time detection and localization, this study applied this model by using mobile devices and drones. The results show that the application of deep learning with UAV can effectively detect various kinds of external wall defects and improve the detection efficiency.

scholarly journals Weakly Supervised Learning for Object Localization Based on an Attention Mechanism

2021 ◽  
Vol 11 (22) ◽  
pp. 10953
Author(s):  
Nojin Park ◽  
Hanseok Ko
Keyword(s):  
Deep Learning ◽  
Experimental Results ◽  
Object Localization ◽  
Localization Accuracy ◽  
Large Size ◽  
Bounding Box ◽  
Improved Performance ◽  
Weakly Supervised ◽  
Detection And Localization ◽  
Activation Map

Recently, deep learning has been successfully applied to object detection and localization tasks in images. When setting up deep learning frameworks for supervised training with large datasets, strongly labeling the objects facilitates good performance; however, the complexity of the image scene and large size of the dataset make this a laborious task. Hence, it is of paramount importance that the expensive work associated with the tasks involving strong labeling, such as bounding box annotation, is reduced. In this paper, we propose a method to perform object localization tasks without bounding box annotation in the training process by means of employing a two-path activation-map-based classifier framework. In particular, we develop an activation-map-based framework to judicially control the attention map in the perception branch by adding a two-feature extractor so that better attention weights can be distributed to induce improved performance. The experimental results indicate that our method surpasses the performance of the existing deep learning models based on weakly supervised object localization. The experimental results show that the proposed method achieves the best performance, with 75.21% Top-1 classification accuracy and 55.15% Top-1 localization accuracy on the CUB-200-2011 dataset.

scholarly journals Real-Time 3D Multi-Object Detection and Localization Based on Deep Learning for Road and Railway Smart Mobility

2021 ◽  
Vol 7 (8) ◽  
pp. 145
Author(s):  
Antoine Mauri ◽  
Redouane Khemmar ◽  
Benoit Decoux ◽  
Madjid Haddad ◽  
Rémi Boutteau
Keyword(s):  
Deep Learning ◽  
Object Detection ◽  
Real Time ◽  
Video Game ◽  
Autonomous Vehicles ◽  
Object Localization ◽  
Driver Assistance Systems ◽  
Smart Mobility ◽  
Bounding Boxes ◽  
Detection And Localization

For smart mobility, autonomous vehicles, and advanced driver-assistance systems (ADASs), perception of the environment is an important task in scene analysis and understanding. Better perception of the environment allows for enhanced decision making, which, in turn, enables very high-precision actions. To this end, we introduce in this work a new real-time deep learning approach for 3D multi-object detection for smart mobility not only on roads, but also on railways. To obtain the 3D bounding boxes of the objects, we modified a proven real-time 2D detector, YOLOv3, to predict 3D object localization, object dimensions, and object orientation. Our method has been evaluated on KITTI’s road dataset as well as on our own hybrid virtual road/rail dataset acquired from the video game Grand Theft Auto (GTA) V. The evaluation of our method on these two datasets shows good accuracy, but more importantly that it can be used in real-time conditions, in road and rail traffic environments. Through our experimental results, we also show the importance of the accuracy of prediction of the regions of interest (RoIs) used in the estimation of 3D bounding box parameters.

scholarly journals Adversarial Learning for Effective Detector Training via Synthetic Data

2020 ◽  
pp. short16-1-short16-9
Author(s):  
Vadim Gorbachev ◽  
Andrey Nikitin ◽  
Ilya Basharov
Keyword(s):  
Real Life ◽  
Synthetic Data ◽  
Real Data ◽  
3D Models ◽  
Training Data ◽  
Real World Data ◽  
Aerial Vehicle ◽  
Effective Use ◽  
Detection And Localization ◽  
Direct Use

Current neural network-based algorithms for object detection require a huge amount of training data. Creation and annotation of specific datasets for real-life applications require significant human and time resources that are not always available. This issue substantially prevents the successful deployment of AI algorithms in industrial tasks. One possible solutions is a synthesis of train images by rendering 3D models of target objects, which allows effortless automatic annotation. However, direct use of synthetic training datasets does not usually result in an increase of the algorithms’ quality on test data due to differences in data domains. In this paper, we propose the adversarial architecture and training method for a CNN-based detector, which allows the effective use of synthesized images in case of a lack of labeled real-world data. The method was successfully tested on real data and applied for the development of unmanned aerial vehicle (UAV) detection and localization system.

scholarly journals USING EDGECONV TO IMPROVE 3D OBJECT DETECTION FROM RGB-D DATA

2019 ◽  
Vol XLII-2/W13 ◽  
pp. 835-839
Author(s):  
W. Lin ◽  
Y. Chen ◽  
C. Wang ◽  
J. Li
Keyword(s):  
Deep Learning ◽  
Large Scale ◽  
Detection Efficiency ◽  
Point Clouds ◽  
Object Localization ◽  
Average Precision ◽  
Structure Information ◽  
Bounding Boxes ◽  
3D Object Detection ◽  
Deep Learning Model

<p><strong>Abstract.</strong> In this paper, we proposed a novel 3D deep learning model for object localization and object bounding boxes estimation. To increase the detection efficiency of small objects in the large scale scenes, the local neighbourhood geometric structure information of objects has been taken into the Edgeconv model, which can operate the original point clouds. We evaluated the 3D bounding box with high resolution in the RGB-D dataset and acquired stable effectiveness even under the sparse points and the strong occlusion. The experimental results indicate that our method achieved the higher mean average precision and better IOU of bounding boxes in SUN RGB-D dataset and KITTI benchmark.</p>

scholarly journals Overcoming detection loss and noise in squeezing-based optical sensing

2021 ◽  
Vol 7 (1) ◽  
Author(s):  
Gaetano Frascella ◽  
Sascha Agne ◽  
Farid Ya. Khalili ◽  
Maria V. Chekhova
Keyword(s):  
Shot Noise ◽  
Optical Sensing ◽  
Detection Efficiency ◽  
Signal To Noise Ratio ◽  
Real Life ◽  
Squeezed States ◽  
Squeezed Light ◽  
Noise Limit ◽  
Imaging And Spectroscopy ◽  
Shot Noise Limit

AbstractAmong the known resources of quantum metrology, one of the most practical and efficient is squeezing. Squeezed states of atoms and light improve the sensing of the phase, magnetic field, polarization, mechanical displacement. They promise to considerably increase signal-to-noise ratio in imaging and spectroscopy, and are already used in real-life gravitational-wave detectors. But despite being more robust than other states, they are still very fragile, which narrows the scope of their application. In particular, squeezed states are useless in measurements where the detection is inefficient or the noise is high. Here, we experimentally demonstrate a remedy against loss and noise: strong noiseless amplification before detection. This way, we achieve loss-tolerant operation of an interferometer fed with squeezed and coherent light. With only 50% detection efficiency and with noise exceeding the level of squeezed light more than 50 times, we overcome the shot-noise limit by 6 dB. Sub-shot-noise phase sensitivity survives up to 87% loss. Application of this technique to other types of optical sensing and imaging promises a full use of quantum resources in these fields.

scholarly journals Identifying the Branch of Kiwifruit Based on Unmanned Aerial Vehicle (UAV) Images Using Deep Learning Method

Sensors ◽  
2021 ◽  
Vol 21 (13) ◽  
pp. 4442
Author(s):  
Zijie Niu ◽  
Juntao Deng ◽  
Xu Zhang ◽  
Jun Zhang ◽  
Shijia Pan ◽  
...  
Keyword(s):  
Deep Learning ◽  
Unmanned Aerial Vehicle ◽  
Semantic Segmentation ◽  
Dynamic Monitoring ◽  
Support Vector ◽  
Distribution Maps ◽  
Time Operation ◽  
Aerial Vehicle ◽  
Uav Images ◽  
Segmentation Image

It is important to obtain accurate information about kiwifruit vines to monitoring their physiological states and undertake precise orchard operations. However, because vines are small and cling to trellises, and have branches laying on the ground, numerous challenges exist in the acquisition of accurate data for kiwifruit vines. In this paper, a kiwifruit canopy distribution prediction model is proposed on the basis of low-altitude unmanned aerial vehicle (UAV) images and deep learning techniques. First, the location of the kiwifruit plants and vine distribution are extracted from high-precision images collected by UAV. The canopy gradient distribution maps with different noise reduction and distribution effects are generated by modifying the threshold and sampling size using the resampling normalization method. The results showed that the accuracies of the vine segmentation using PSPnet, support vector machine, and random forest classification were 71.2%, 85.8%, and 75.26%, respectively. However, the segmentation image obtained using depth semantic segmentation had a higher signal-to-noise ratio and was closer to the real situation. The average intersection over union of the deep semantic segmentation was more than or equal to 80% in distribution maps, whereas, in traditional machine learning, the average intersection was between 20% and 60%. This indicates the proposed model can quickly extract the vine distribution and plant position, and is thus able to perform dynamic monitoring of orchards to provide real-time operation guidance.

scholarly journals Orchard Mapping with Deep Learning Semantic Segmentation

Sensors ◽  
2021 ◽  
Vol 21 (11) ◽  
pp. 3813
Author(s):  
Athanasios Anagnostis ◽  
Aristotelis C. Tagarakis ◽  
Dimitrios Kateris ◽  
Vasileios Moysiadis ◽  
Claus Grøn Sørensen ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Semantic Segmentation ◽  
Automated Detection ◽  
Aerial Images ◽  
Training Dataset ◽  
Field Boundary ◽  
Different Seasons ◽  
Detection And Localization ◽  
Different Levels

This study aimed to propose an approach for orchard trees segmentation using aerial images based on a deep learning convolutional neural network variant, namely the U-net network. The purpose was the automated detection and localization of the canopy of orchard trees under various conditions (i.e., different seasons, different tree ages, different levels of weed coverage). The implemented dataset was composed of images from three different walnut orchards. The achieved variability of the dataset resulted in obtaining images that fell under seven different use cases. The best-trained model achieved 91%, 90%, and 87% accuracy for training, validation, and testing, respectively. The trained model was also tested on never-before-seen orthomosaic images or orchards based on two methods (oversampling and undersampling) in order to tackle issues with out-of-the-field boundary transparent pixels from the image. Even though the training dataset did not contain orthomosaic images, it achieved performance levels that reached up to 99%, demonstrating the robustness of the proposed approach.

scholarly journals Evaluation Model of Operation State Based on Deep Learning for Smart Meter

Energies ◽  
2021 ◽  
Vol 14 (15) ◽  
pp. 4674
Author(s):  
Qingsheng Zhao ◽  
Juwen Mu ◽  
Xiaoqing Han ◽  
Dingkang Liang ◽  
Xuping Wang
Keyword(s):  
Deep Learning ◽  
Power Consumption ◽  
Detection Efficiency ◽  
Evaluation Model ◽  
Smart Meter ◽  
Smart Meters ◽  
Abnormal Detection ◽  
Prediction Residual ◽  
Threshold Setting ◽  
Training Efficiency

The operation state detection of numerous smart meters is a significant problem caused by manual on-site testing. This paper addresses the problem of improving the malfunction detection efficiency of smart meters using deep learning and proposes a novel evaluation model of operation state for smart meter. This evaluation model adopts recurrent neural networks (RNN) to predict power consumption. According to the prediction residual between predicted power consumption and the observed power consumption, the malfunctioning smart meter is detected. The training efficiency for the prediction model is improved by using transfer learning (TL). This evaluation uses an accumulator algorithm and threshold setting with flexibility for abnormal detection. In the simulation experiment, the detection principle is demonstrated to improve efficient replacement and extend the average using time of smart meters. The effectiveness of the evaluation model was verified on the actual station dataset. It has accurately detected the operation state of smart meters.

Sign in / Sign up

Export Citation Format

Share Document