scholarly journals Augmenting Crop Detection for Precision Agriculture with Deep Visual Transfer Learning—A Case Study of Bale Detection

2020 ◽  
Vol 13 (1) ◽  
pp. 23
Author(s):  
Wei Zhao ◽  
William Yamada ◽  
Tianxin Li ◽  
Matthew Digman ◽  
Troy Runge
Keyword(s):  
Object Detection ◽  
Transfer Learning ◽  
Precision Agriculture ◽  
Crop Production ◽  
Domain Adaptation ◽  
Training Data ◽  
Detection Accuracy ◽  
Detection Model ◽  
Agriculture Products

In recent years, precision agriculture has been researched to increase crop production with less inputs, as a promising means to meet the growing demand of agriculture products. Computer vision-based crop detection with unmanned aerial vehicle (UAV)-acquired images is a critical tool for precision agriculture. However, object detection using deep learning algorithms rely on a significant amount of manually prelabeled training datasets as ground truths. Field object detection, such as bales, is especially difficult because of (1) long-period image acquisitions under different illumination conditions and seasons; (2) limited existing prelabeled data; and (3) few pretrained models and research as references. This work increases the bale detection accuracy based on limited data collection and labeling, by building an innovative algorithms pipeline. First, an object detection model is trained using 243 images captured with good illimitation conditions in fall from the crop lands. In addition, domain adaptation (DA), a kind of transfer learning, is applied for synthesizing the training data under diverse environmental conditions with automatic labels. Finally, the object detection model is optimized with the synthesized datasets. The case study shows the proposed method improves the bale detecting performance, including the recall, mean average precision (mAP), and F measure (F1 score), from averages of 0.59, 0.7, and 0.7 (the object detection) to averages of 0.93, 0.94, and 0.89 (the object detection + DA), respectively. This approach could be easily scaled to many other crop field objects and will significantly contribute to precision agriculture.

scholarly journals Transcription Alignment of Historical Vietnamese Manuscripts without Human-Annotated Learning Samples

2021 ◽  
Vol 11 (11) ◽  
pp. 4894
Author(s):  
Anna Scius-Bertrand ◽  
Michael Jungo ◽  
Beat Wolf ◽  
Andreas Fischer ◽  
Marc Bui
Keyword(s):  
Object Detection ◽  
State Of The Art ◽  
Positive Impact ◽  
Detection System ◽  
Training Data ◽  
Detection Accuracy ◽  
Current State ◽  
Alignment Task ◽  
Scanned Image ◽  
Automatic Transcription

The current state of the art for automatic transcription of historical manuscripts is typically limited by the requirement of human-annotated learning samples, which are are necessary to train specific machine learning models for specific languages and scripts. Transcription alignment is a simpler task that aims to find a correspondence between text in the scanned image and its existing Unicode counterpart, a correspondence which can then be used as training data. The alignment task can be approached with heuristic methods dedicated to certain types of manuscripts, or with weakly trained systems reducing the required amount of annotations. In this article, we propose a novel learning-based alignment method based on fully convolutional object detection that does not require any human annotation at all. Instead, the object detection system is initially trained on synthetic printed pages using a font and then adapted to the real manuscripts by means of self-training. On a dataset of historical Vietnamese handwriting, we demonstrate the feasibility of annotation-free alignment as well as the positive impact of self-training on the character detection accuracy, reaching a detection accuracy of 96.4% with a YOLOv5m model without using any human annotation.

scholarly journals Investigating the Potential of Network Optimization for a Constrained Object Detection Problem

2021 ◽  
Vol 7 (4) ◽  
pp. 64
Author(s):  
Tanguy Ophoff ◽  
Cédric Gullentops ◽  
Kristof Van Beeck ◽  
Toon Goedemé
Keyword(s):  
Computational Complexity ◽  
Object Detection ◽  
Network Optimization ◽  
Real Life ◽  
Optimization Techniques ◽  
Training Data ◽  
Single Shot ◽  
Standard Object ◽  
Number Of Classes

Object detection models are usually trained and evaluated on highly complicated, challenging academic datasets, which results in deep networks requiring lots of computations. However, a lot of operational use-cases consist of more constrained situations: they have a limited number of classes to be detected, less intra-class variance, less lighting and background variance, constrained or even fixed camera viewpoints, etc. In these cases, we hypothesize that smaller networks could be used without deteriorating the accuracy. However, there are multiple reasons why this does not happen in practice. Firstly, overparameterized networks tend to learn better, and secondly, transfer learning is usually used to reduce the necessary amount of training data. In this paper, we investigate how much we can reduce the computational complexity of a standard object detection network in such constrained object detection problems. As a case study, we focus on a well-known single-shot object detector, YoloV2, and combine three different techniques to reduce the computational complexity of the model without reducing its accuracy on our target dataset. To investigate the influence of the problem complexity, we compare two datasets: a prototypical academic (Pascal VOC) and a real-life operational (LWIR person detection) dataset. The three optimization steps we exploited are: swapping all the convolutions for depth-wise separable convolutions, perform pruning and use weight quantization. The results of our case study indeed substantiate our hypothesis that the more constrained a problem is, the more the network can be optimized. On the constrained operational dataset, combining these optimization techniques allowed us to reduce the computational complexity with a factor of 349, as compared to only a factor 9.8 on the academic dataset. When running a benchmark on an Nvidia Jetson AGX Xavier, our fastest model runs more than 15 times faster than the original YoloV2 model, whilst increasing the accuracy by 5% Average Precision (AP).

scholarly journals Automatic Roadway Features Detection with Oriented Object Detection

2021 ◽  
Vol 11 (8) ◽  
pp. 3531
Author(s):  
Hesham M. Eraqi ◽  
Karim Soliman ◽  
Dalia Said ◽  
Omar R. Elezaby ◽  
Mohamed N. Moustafa ◽  
...  
Keyword(s):  
Object Detection ◽  
Safety Evaluation ◽  
Autonomous Driving ◽  
Detection Accuracy ◽  
The Road ◽  
Detection Model ◽  
Detection Approach ◽  
Roadway Safety ◽  
Safety Features ◽  
Oriented Object

Extensive research efforts have been devoted to identify and improve roadway features that impact safety. Maintaining roadway safety features relies on costly manual operations of regular road surveying and data analysis. This paper introduces an automatic roadway safety features detection approach, which harnesses the potential of artificial intelligence (AI) computer vision to make the process more efficient and less costly. Given a front-facing camera and a global positioning system (GPS) sensor, the proposed system automatically evaluates ten roadway safety features. The system is composed of an oriented (or rotated) object detection model, which solves an orientation encoding discontinuity problem to improve detection accuracy, and a rule-based roadway safety evaluation module. To train and validate the proposed model, a fully-annotated dataset for roadway safety features extraction was collected covering 473 km of roads. The proposed method baseline results are found encouraging when compared to the state-of-the-art models. Different oriented object detection strategies are presented and discussed, and the developed model resulted in improving the mean average precision (mAP) by 16.9% when compared with the literature. The roadway safety feature average prediction accuracy is 84.39% and ranges between 91.11% and 63.12%. The introduced model can pervasively enable/disable autonomous driving (AD) based on safety features of the road; and empower connected vehicles (CV) to send and receive estimated safety features, alerting drivers about black spots or relatively less-safe segments or roads.

Small Targets Detection for Transmission Tower Based on SRGAN and Faster RCNN

2021 ◽  
Vol 14 ◽  
Author(s):  
Runze Liu ◽  
Guangwei Yan ◽  
Hui He ◽  
Yubin An ◽  
Ting Wang ◽  
...  
Keyword(s):  
Object Detection ◽  
Super Resolution ◽  
Generative Adversarial Networks ◽  
Stable Operation ◽  
Detection Accuracy ◽  
Small Object ◽  
Detection Model ◽  
Tower Equipment ◽  
Small Object Detection ◽  
Small Targets

Background: Power line inspection is essential to ensure the safe and stable operation of the power system. Object detection for tower equipment can significantly improve inspection efficiency. However, due to the low resolution of small targets and limited features, the detection accuracy of small targets is not easy to improve. Objective: This study aimed to improve the tiny targets’ resolution while making the small target's texture and detailed features more prominent to be perceived by the detection model. Methods: In this paper, we propose an algorithm that employs generative adversarial networks to improve small objects' detection accuracy. First, the original image is converted into a super-resolution one by a super-resolution reconstruction network (SRGAN). Then the object detection framework Faster RCNN is utilized to detect objects on the super-resolution images. Result: The experimental results on two small object recognition datasets show that the model proposed in this paper has good robustness. It can especially detect the targets missed by Faster RCNN, which indicates that SRGAN can effectively enhance the detailed information of small targets by improving the resolution. Conclusion: We found that higher resolution data is conducive to obtaining more detailed information of small targets, which can help the detection algorithm achieve higher accuracy. The small object detection model based on the generative adversarial network proposed in this paper is feasible and more efficient. Compared with Faster RCNN, this model has better performance on small object detection.

scholarly journals Object Detection Model Based on Deep Dilated Convolutional Networks by Fusing Transfer Learning

IEEE Access ◽  
2019 ◽  
Vol 7 ◽  
pp. 178699-178709
Author(s):  
Yu Quan ◽  
Zhixin Li ◽  
Canlong Zhang ◽  
Huifang Ma
Keyword(s):  
Object Detection ◽  
Transfer Learning ◽  
Detection Model ◽  
Convolutional Networks ◽  
Model Based

scholarly journals Obtaining Urban Waterlogging Depths from Video Images Using Synthetic Image Data

2020 ◽  
Vol 12 (6) ◽  
pp. 1014
Author(s):  
Jingchao Jiang ◽  
Cheng-Zhi Qin ◽  
Juan Yu ◽  
Changxiu Cheng ◽  
Junzhi Liu ◽  
...  
Keyword(s):  
Object Detection ◽  
Data Augmentation ◽  
Open Data ◽  
Image Data ◽  
Training Data ◽  
Synthetic Image ◽  
Detection Model ◽  
Video Images ◽  
Image Dataset ◽  
Water Surfaces

Reference objects in video images can be used to indicate urban waterlogging depths. The detection of reference objects is the key step to obtain waterlogging depths from video images. Object detection models with convolutional neural networks (CNNs) have been utilized to detect reference objects. These models require a large number of labeled images as the training data to ensure the applicability at a city scale. However, it is hard to collect a sufficient number of urban flooding images containing valuable reference objects, and manually labeling images is time-consuming and expensive. To solve the problem, we present a method to synthesize image data as the training data. Firstly, original images containing reference objects and original images with water surfaces are collected from open data sources, and reference objects and water surfaces are cropped from these original images. Secondly, the reference objects and water surfaces are further enriched via data augmentation techniques to ensure the diversity. Finally, the enriched reference objects and water surfaces are combined to generate a synthetic image dataset with annotations. The synthetic image dataset is further used for training an object detection model with CNN. The waterlogging depths are calculated based on the reference objects detected by the trained model. A real video dataset and an artificial image dataset are used to evaluate the effectiveness of the proposed method. The results show that the detection model trained using the synthetic image dataset can effectively detect reference objects from images, and it can achieve acceptable accuracies of waterlogging depths based on the detected reference objects. The proposed method has the potential to monitor waterlogging depths at a city scale.

scholarly journals Comparative Research on Deep Learning Approaches for Airplane Detection from Very High-Resolution Satellite Images

2020 ◽  
Vol 12 (3) ◽  
pp. 458 ◽  
Author(s):  
Ugur Alganci ◽  
Mehmet Soydas ◽  
Elif Sertel
Keyword(s):  
Deep Learning ◽  
High Resolution ◽  
Object Detection ◽  
Satellite Images ◽  
Training Data ◽  
Object Localization ◽  
Detection Accuracy ◽  
Single Shot ◽  
High Resolution Satellite Images ◽  
Very High

Object detection from satellite images has been a challenging problem for many years. With the development of effective deep learning algorithms and advancement in hardware systems, higher accuracies have been achieved in the detection of various objects from very high-resolution (VHR) satellite images. This article provides a comparative evaluation of the state-of-the-art convolutional neural network (CNN)-based object detection models, which are Faster R-CNN, Single Shot Multi-box Detector (SSD), and You Look Only Once-v3 (YOLO-v3), to cope with the limited number of labeled data and to automatically detect airplanes in VHR satellite images. Data augmentation with rotation, rescaling, and cropping was applied on the test images to artificially increase the number of training data from satellite images. Moreover, a non-maximum suppression algorithm (NMS) was introduced at the end of the SSD and YOLO-v3 flows to get rid of the multiple detection occurrences near each detected object in the overlapping areas. The trained networks were applied to five independent VHR test images that cover airports and their surroundings to evaluate their performance objectively. Accuracy assessment results of the test regions proved that Faster R-CNN architecture provided the highest accuracy according to the F1 scores, average precision (AP) metrics, and visual inspection of the results. The YOLO-v3 ranked as second, with a slightly lower performance but providing a balanced trade-off between accuracy and speed. The SSD provided the lowest detection performance, but it was better in object localization. The results were also evaluated in terms of the object size and detection accuracy manner, which proved that large- and medium-sized airplanes were detected with higher accuracy.

scholarly journals Towards a Better Understanding of Transfer Learning for Medical Imaging: A Case Study

2020 ◽  
Vol 10 (13) ◽  
pp. 4523 ◽  
Author(s):  
Laith Alzubaidi ◽  
Mohammed A. Fadhel ◽  
Omran Al-Shamma ◽  
Jinglan Zhang ◽  
J. Santamaría ◽  
...  
Keyword(s):  
Medical Imaging ◽  
Transfer Learning ◽  
Foot Ulcer ◽  
Diabetic Foot Ulcer ◽  
Training Data ◽  
Classification Task ◽  
Natural Image ◽  
Target Domain ◽  
Proposed Model

One of the main challenges of employing deep learning models in the field of medicine is a lack of training data due to difficulty in collecting and labeling data, which needs to be performed by experts. To overcome this drawback, transfer learning (TL) has been utilized to solve several medical imaging tasks using pre-trained state-of-the-art models from the ImageNet dataset. However, there are primary divergences in data features, sizes, and task characteristics between the natural image classification and the targeted medical imaging tasks. Therefore, TL can slightly improve performance if the source domain is completely different from the target domain. In this paper, we explore the benefit of TL from the same and different domains of the target tasks. To do so, we designed a deep convolutional neural network (DCNN) model that integrates three ideas including traditional and parallel convolutional layers and residual connections along with global average pooling. We trained the proposed model against several scenarios. We utilized the same and different domain TL with the diabetic foot ulcer (DFU) classification task and with the animal classification task. We have empirically shown that the source of TL from the same domain can significantly improve the performance considering a reduced number of images in the same domain of the target dataset. The proposed model with the DFU dataset achieved F1-score value of 86.6% when trained from scratch, 89.4% with TL from a different domain of the targeted dataset, and 97.6% with TL from the same domain of the targeted dataset.

scholarly journals Weapon Detection Using YOLO V3 for Smart Surveillance System

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Sanam Narejo ◽  
Bishwajeet Pandey ◽  
Doris Esenarro vargas ◽  
Ciro Rodriguez ◽  
M. Rizwan Anjum
Keyword(s):  
Object Detection ◽  
Transfer Learning ◽  
Surveillance System ◽  
Human Life ◽  
Automated System ◽  
Detection Model ◽  
Smart Surveillance ◽  
Computer Based ◽  
Smart Surveillance System ◽  
Detection And Recognition

Every year, a large amount of population reconciles gun-related violence all over the world. In this work, we develop a computer-based fully automated system to identify basic armaments, particularly handguns and rifles. Recent work in the field of deep learning and transfer learning has demonstrated significant progress in the areas of object detection and recognition. We have implemented YOLO V3 “You Only Look Once” object detection model by training it on our customized dataset. The training results confirm that YOLO V3 outperforms YOLO V2 and traditional convolutional neural network (CNN). Additionally, intensive GPUs or high computation resources were not required in our approach as we used transfer learning for training our model. Applying this model in our surveillance system, we can attempt to save human life and accomplish reduction in the rate of manslaughter or mass killing. Additionally, our proposed system can also be implemented in high-end surveillance and security robots to detect a weapon or unsafe assets to avoid any kind of assault or risk to human life.

Sign in / Sign up

Export Citation Format

Share Document