Building Robust Industrial Applicable Object Detection Models using Transfer Learning and Single Pass Deep Learning Architectures

The breaching of tailings pond dams may lead to casualties and environmental pollution; therefore, timely and accurate monitoring is an essential aspect of managing such structures and preventing accidents. Remote sensing technology is suitable for the regular extraction and monitoring of tailings pond information. However, traditional remote sensing is inefficient and unsuitable for the frequent extraction of large volumes of highly precise information. Object detection, based on deep learning, provides a solution to this problem. Most remote sensing imagery applications for tailings pond object detection using deep learning are based on computer vision, utilizing the true-color triple-band data of high spatial resolution imagery for information extraction. The advantage of remote sensing image data is their greater number of spectral bands (more than three), providing more abundant spectral information. There is a lack of research on fully harnessing multispectral band information to improve the detection precision of tailings ponds. Accordingly, using a sample dataset of tailings pond satellite images from the Gaofen-1 high-resolution Earth observation satellite, we improved the Faster R-CNN deep learning object detection model by increasing the inputs from three true-color bands to four multispectral bands. Moreover, we used the attention mechanism to recalibrate the input contributions. Subsequently, we used a step-by-step transfer learning method to improve and gradually train our model. The improved model could fully utilize the near-infrared (NIR) band information of the images to improve the precision of tailings pond detection. Compared with that of the three true-color band input models, the tailings pond detection average precision (AP) and recall notably improved in our model, with the AP increasing from 82.3% to 85.9% and recall increasing from 65.4% to 71.9%. This research could serve as a reference for using multispectral band information from remote sensing images in the construction and application of deep learning models.

Download Full-text

An IoT‐based human detection system for complex industrial environment with deep learning architectures and transfer learning

International Journal of Intelligent Systems ◽

10.1002/int.22472 ◽

2021 ◽

Author(s):

Imran Ahmed ◽

Marco Anisetti ◽

Gwanggil Jeon

Keyword(s):

Deep Learning ◽

Transfer Learning ◽

Detection System ◽

Human Detection ◽

Industrial Environment ◽

Learning Architectures

Download Full-text

Implementation of Object Recognition Algorithm to enhance Manufacturing and Maintenance Tasks on an Aircraft

10.32920/ryerson.14637387.v1 ◽

2021 ◽

Author(s):

Abhinav Sundar

Keyword(s):

Neural Network ◽

Deep Learning ◽

Object Recognition ◽

Object Detection ◽

Convolutional Neural Network ◽

Transfer Learning ◽

Learning Algorithm ◽

Recognition Algorithm ◽

Recognition Algorithms ◽

Aerospace Assembly

The objective of this thesis was to evaluate the viability of implementation of an object recognition algorithm driven by deep learning for aerospace manufacturing, maintenance and assembly tasks. Comparison research has found that current computer vision methods such as, spatial mapping was limited to macro-object recognition because of its nodal wireframe analysis. An optical object recognition algorithm was trained to learn complex geometric and chromatic characteristics, therefore allowing for micro-object recognition, such as cables and other critical components. This thesis investigated the use of a convolutional neural network with object recognition algorithms. The viability of two categories of object recognition algorithms were analyzed: image prediction and object detection. Due to a viral epidemic, this thesis was limited in analytical consistency as resources were not readily available. The prediction-class algorithm was analyzed using a custom dataset comprised of 15 552 images of the MaxFlight V2002 Full Motion Simulator’s inverter system, and a model was created by transfer-learning that dataset onto the InceptionV3 convolutional neural network (CNN). The detection-class algorithm was analyzed using a custom dataset comprised of 100 images of two SUVs of different brand and style, and a model was created by transfer-learning that dataset onto the YOLOv3 deep learning architecture. The tests showed that the object recognition algorithms successfully identified the components with good accuracy, 99.97% mAP for prediction-class and 89.54% mAP. For detection-class. The accuracies and data collected with literature review found that object detection algorithms are accuracy, created for live -feed analysis and were suitable for the significant applications of AVI and aircraft assembly. In the future, a larger dataset needs to be complied to increase reliability and a custom convolutional neural network and deep learning algorithm needs to be developed specifically for aerospace assembly, maintenance and manufacturing applications.

Download Full-text

Developing an Image-Based Deep Learning Framework for Automatic Scoring of The Pentagon Drawing Test

Journal of Alzheimer s Disease ◽

10.3233/jad-210714 ◽

2021 ◽

pp. 1-11

Author(s):

Yike Li ◽

Jiajie Guo ◽

Peikai Yang

Keyword(s):

Deep Learning ◽

Object Detection ◽

Transfer Learning ◽

High Efficiency ◽

Characteristic Curve ◽

Data Partitioning ◽

Training Data ◽

Drawing Test ◽

Automatic Scoring ◽

Efficiency And Reliability

Background: The Pentagon Drawing Test (PDT) is a common assessment for visuospatial function. Evaluating the PDT by artificial intelligence can improve efficiency and reliability in the big data era. This study aimed to develop a deep learning (DL) framework for automatic scoring of the PDT based on image data. Methods: A total of 823 PDT photos were retrospectively collected and preprocessed into black-and-white, square-shape images. Stratified fivefold cross-validation was applied for training and testing. Two strategies based on convolutional neural networks were compared. The first strategy was to perform an image classification task using supervised transfer learning. The second strategy was designed with an object detection model for recognizing the geometric shapes in the figure, followed by a predetermined algorithm to score based on their classes and positions. Results: On average, the first framework demonstrated 62%accuracy, 62%recall, 65%precision, 63%specificity, and 0.72 area under the receiver operating characteristic curve. This performance was substantially outperformed by the second framework, with averages of 94%, 95%, 93%, 93%, and 0.95, respectively. Conclusion: An image-based DL framework based on the object detection approach may be clinically applicable for automatic scoring of the PDT with high efficiency and reliability. With a limited sample size, transfer learning should be used with caution if the new images are distinct from the previous training data. Partitioning the problem-solving workflow into multiple simple tasks should facilitate model selection, improve performance, and allow comprehensible logic of the DL framework.

Download Full-text

Image-Based Goat Breed Identification and Localization Using Deep Learning

International Journal of Computer Vision and Image Processing ◽

10.4018/ijcvip.2020100105 ◽

2020 ◽

Vol 10 (4) ◽

pp. 74-96

Author(s):

Pritam Ghosh ◽

Subhranil Mustafi ◽

Satyendra Nath Mandal

Keyword(s):

Deep Learning ◽

Object Detection ◽

Transfer Learning ◽

Digital Images ◽

Evaluation Metrics ◽

Natural Environments ◽

Goat Breed ◽

Pure Breed ◽

Detection Model ◽

Detection Evaluation

In this paper an attempt has been made to identify six different goat breeds from pure breed goat images. The images of goat breeds have been captured from different organized registered goat farms in India, and almost two thousand digital images of individual goats were captured in restricted (to get similar image background) and unrestricted (natural) environments without imposing stress to animals. A pre-trained deep learning-based object detection model called Faster R-CNN has been fine-tuned by using transfer-learning on the acquired images for automatic classification and localization of goat breeds. This fine-tuned model is able to locate the goat (localize) and classify (identify) its breed in the image. The Pascal VOC object detection evaluation metrics have been used to evaluate this model. Finally, comparison has been made with prediction accuracies of different technologies used for different animal breed identification.

Download Full-text

Object Detection in Monocular Infrared Images Using Classification – Regresion Deep Learning Architectures

2019 IEEE 15th International Conference on Intelligent Computer Communication and Processing (ICCP) ◽

10.1109/iccp48234.2019.8959763 ◽

2019 ◽

Author(s):

Raluca Brehar ◽

Flaviu Vancea ◽

Tiberiu Marita ◽

Cristian Vancea ◽

Sergiu Nedevschi

Keyword(s):

Deep Learning ◽

Object Detection ◽

Infrared Images ◽

Learning Architectures

Download Full-text

An ensemble deep learning method with optimized weights for drone-based water rescue and surveillance

Integrated Computer-Aided Engineering ◽

10.3233/ica-210649 ◽

2021 ◽

pp. 1-15

Author(s):

Jan Ga̧sienica-Józkowy ◽

Mateusz Knapik ◽

Bogusław Cyganek

Keyword(s):

Neural Networks ◽

Deep Learning ◽

Object Detection ◽

Search And Rescue ◽

Deep Convolutional Neural Networks ◽

Voting Weights ◽

Water Rescue ◽

Maritime Search And Rescue ◽

Floating Objects ◽

Learning Architectures

Today’s deep learning architectures, if trained with proper dataset, can be used for object detection in marine search and rescue operations. In this paper a dataset for maritime search and rescue purposes is proposed. It contains aerial-drone videos with 40,000 hand-annotated persons and objects floating in the water, many of small size, which makes them difficult to detect. The second contribution is our proposed object detection method. It is an ensemble composed of a number of the deep convolutional neural networks, orchestrated by the fusion module with the nonlinearly optimized voting weights. The method achieves over 82% of average precision on the new aerial-drone floating objects dataset and outperforms each of the state-of-the-art deep neural networks, such as YOLOv3, -v4, Faster R-CNN, RetinaNet, and SSD300. The dataset is publicly available from the Internet.

Download Full-text