scholarly journals Multiscale Object Detection from Drone Imagery Using Ensemble Transfer Learning

Drones ◽  
2021 ◽  
Vol 5 (3) ◽  
pp. 66
Author(s):  
Rahee Walambe ◽  
Aboli Marathe ◽  
Ketan Kotecha
Keyword(s):  
Object Detection ◽  
Transfer Learning ◽  
Data Augmentation ◽  
Test Time ◽  
Complex Task ◽  
Open Domain ◽  
End User ◽  
Aerial Vehicle ◽  
Uav Images ◽  
Voting Strategy

Object detection in uncrewed aerial vehicle (UAV) images has been a longstanding challenge in the field of computer vision. Specifically, object detection in drone images is a complex task due to objects of various scales such as humans, buildings, water bodies, and hills. In this paper, we present an implementation of ensemble transfer learning to enhance the performance of the base models for multiscale object detection in drone imagery. Combined with a test-time augmentation pipeline, the algorithm combines different models and applies voting strategies to detect objects of various scales in UAV images. The data augmentation also presents a solution to the deficiency of drone image datasets. We experimented with two specific datasets in the open domain: the VisDrone dataset and the AU-AIR Dataset. Our approach is more practical and efficient due to the use of transfer learning and two-level voting strategy ensemble instead of training custom models on entire datasets. The experimentation shows significant improvement in the mAP for both VisDrone and AU-AIR datasets by employing the ensemble transfer learning method. Furthermore, the utilization of voting strategies further increases the 3reliability of the ensemble as the end-user can select and trace the effects of the mechanism for bounding box predictions.

Object Detection in X-ray Images Using Transfer Learning with Data Augmentation

2019 ◽  
Vol 9 (6) ◽  
pp. 2147
Author(s):  
Reagan L. Galvez ◽  
Elmer P. Dadios ◽  
Argel A. Bandala ◽  
Ryan Rhay P. Vicerra
Keyword(s):  
Object Detection ◽  
Transfer Learning ◽  
Data Augmentation ◽  
X Ray

scholarly journals A Wheat Spike Detection Method in UAV Images Based on Improved YOLOv5

2021 ◽  
Vol 13 (16) ◽  
pp. 3095
Author(s):  
Jianqing Zhao ◽  
Xiaohu Zhang ◽  
Jiawei Yan ◽  
Xiaolei Qiu ◽  
Xia Yao ◽  
...  
Keyword(s):  
Object Detection ◽  
Error Detection ◽  
Data Augmentation ◽  
Detection Accuracy ◽  
Single Shot ◽  
Spike Detection ◽  
Detection Algorithms ◽  
Average Accuracy ◽  
Uav Images ◽  
Wheat Spike

Deep-learning-based object detection algorithms have significantly improved the performance of wheat spike detection. However, UAV images crowned with small-sized, highly dense, and overlapping spikes cause the accuracy to decrease for detection. This paper proposes an improved YOLOv5 (You Look Only Once)-based method to detect wheat spikes accurately in UAV images and solve spike error detection and miss detection caused by occlusion conditions. The proposed method introduces data cleaning and data augmentation to improve the generalization ability of the detection network. The network is rebuilt by adding a microscale detection layer, setting prior anchor boxes, and adapting the confidence loss function of the detection layer based on the IoU (Intersection over Union). These refinements improve the feature extraction for small-sized wheat spikes and lead to better detection accuracy. With the confidence weights, the detection boxes in multiresolution images are fused to increase the accuracy under occlusion conditions. The result shows that the proposed method is better than the existing object detection algorithms, such as Faster RCNN, Single Shot MultiBox Detector (SSD), RetinaNet, and standard YOLOv5. The average accuracy (AP) of wheat spike detection in UAV images is 94.1%, which is 10.8% higher than the standard YOLOv5. Thus, the proposed method is a practical way to handle the spike detection in complex field scenarios and provide technical references for field-level wheat phenotype monitoring.

scholarly journals Automatic Garbage Scattered Area Detection with Data Augmentation and Transfer Learning in SUAV Low-Altitude Remote Sensing Images

2020 ◽  
Vol 2020 ◽  
pp. 1-13
Author(s):  
Tengfei You ◽  
Weiyang Chen ◽  
Haifeng Wang ◽  
Yang Yang ◽  
Xinang Liu
Keyword(s):  
Remote Sensing ◽  
Transfer Learning ◽  
Data Augmentation ◽  
Traditional Approach ◽  
Nature Reserves ◽  
Ecological Environment ◽  
Future Research ◽  
Method Transfer ◽  
Aerial Vehicle ◽  
Low Altitude

Cleaning up the garbage timely plays an important role in protecting the ecological environment of nature reserves. The traditional approach adopts manual patrol and centralized cleaning to clean up garbage, which is inefficient. In order to protect the ecological environment of nature reserves, this paper proposes an automatic garbage scattered area detection (GSAD) model based on the state-of-the-art deep learning EfficientDet method, transfer learning, data augmentation, and image blocking. The main contributions of this paper are (1) we build a garbage sample dataset based on small unmanned aerial vehicle (SUAV) low-altitude remote sensing and (2) we propose a novel data augmentation approach based on garbage scattered area detection and (3) this paper establishes a model (GSAD) for garbage scattered area detection based on data augmentation, transfer learning, and image blocking and gives future research directions. Experimental results show that the GSAD model can achieve the F1-score of 95.11% and average detection time of 1.096 s.

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.

A dual neural network for object detection in UAV images

2021 ◽  
Vol 443 ◽  
pp. 292-301
Author(s):  
Gangyi Tian ◽  
Jianran Liu ◽  
Wenyuan Yang
Keyword(s):  
Neural Network ◽  
Object Detection ◽  
Uav Images

scholarly journals Reference Measurements in Developing UAV Systems for Detecting Pests, Weeds, and Diseases

2021 ◽  
Vol 13 (7) ◽  
pp. 1238
Author(s):  
Jere Kaivosoja ◽  
Juho Hautsalo ◽  
Jaakko Heikkinen ◽  
Lea Hiltunen ◽  
Pentti Ruuttunen ◽  
...  
Keyword(s):  
Reference Data ◽  
Measurement Techniques ◽  
Synthetic Data ◽  
Ground Truth ◽  
Precision Farming ◽  
Aerial Imaging ◽  
Aerial Vehicle ◽  
Uav Images ◽  
Reference Measurements

The development of UAV (unmanned aerial vehicle) imaging technologies for precision farming applications is rapid, and new studies are published frequently. In cases where measurements are based on aerial imaging, there is the need to have ground truth or reference data in order to develop reliable applications. However, in several precision farming use cases such as pests, weeds, and diseases detection, the reference data can be subjective or relatively difficult to capture. Furthermore, the collection of reference data is usually laborious and time consuming. It also appears that it is difficult to develop generalisable solutions for these areas. This review studies previous research related to pests, weeds, and diseases detection and mapping using UAV imaging in the precision farming context, underpinning the applied reference measurement techniques. The majority of the reviewed studies utilised subjective visual observations of UAV images, and only a few applied in situ measurements. The conclusion of the review is that there is a lack of quantitative and repeatable reference data measurement solutions in the areas of mapping pests, weeds, and diseases. In addition, the results that the studies present should be reflected in the applied references. An option in the future approach could be the use of synthetic data as reference.

scholarly journals Classification of Space Objects by Using Deep Learning with Micro-Doppler Signature Images

Sensors ◽  
2021 ◽  
Vol 21 (13) ◽  
pp. 4365
Author(s):  
Kwangyong Jung ◽  
Jae-In Lee ◽  
Nammoon Kim ◽  
Sunjin Oh ◽  
Dong-Wook Seo
Keyword(s):  
Transfer Learning ◽  
Data Augmentation ◽  
Doppler Frequency ◽  
Extraction Methods ◽  
Classification Performance ◽  
Reconstruction Method ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Space Objects ◽  
Target Characteristics

Radar target classification is an important task in the missile defense system. State-of-the-art studies using micro-doppler frequency have been conducted to classify the space object targets. However, existing studies rely highly on feature extraction methods. Therefore, the generalization performance of the classifier is limited and there is room for improvement. Recently, to improve the classification performance, the popular approaches are to build a convolutional neural network (CNN) architecture with the help of transfer learning and use the generative adversarial network (GAN) to increase the training datasets. However, these methods still have drawbacks. First, they use only one feature to train the network. Therefore, the existing methods cannot guarantee that the classifier learns more robust target characteristics. Second, it is difficult to obtain large amounts of data that accurately mimic real-world target features by performing data augmentation via GAN instead of simulation. To mitigate the above problem, we propose a transfer learning-based parallel network with the spectrogram and the cadence velocity diagram (CVD) as the inputs. In addition, we obtain an EM simulation-based dataset. The radar-received signal is simulated according to a variety of dynamics using the concept of shooting and bouncing rays with relative aspect angles rather than the scattering center reconstruction method. Our proposed model is evaluated on our generated dataset. The proposed method achieved about 0.01 to 0.39% higher accuracy than the pre-trained networks with a single input feature.

scholarly journals A Two-Phase Fashion Apparel Detection Method Based on YOLOv4

2021 ◽  
Vol 11 (9) ◽  
pp. 3782
Author(s):  
Chu-Hui Lee ◽  
Chen-Wei Lin
Keyword(s):  
Object Detection ◽  
Transfer Learning ◽  
Detection Method ◽  
Phase Transfer ◽  
Recognition Task ◽  
Phase Detection ◽  
Target Domain ◽  
Two Phase ◽  
Detection Technology ◽  
Fashion Apparel

Object detection is one of the important technologies in the field of computer vision. In the area of fashion apparel, object detection technology has various applications, such as apparel recognition, apparel detection, fashion recommendation, and online search. The recognition task is difficult for a computer because fashion apparel images have different characteristics of clothing appearance and material. Currently, fast and accurate object detection is the most important goal in this field. In this study, we proposed a two-phase fashion apparel detection method named YOLOv4-TPD (YOLOv4 Two-Phase Detection), based on the YOLOv4 algorithm, to address this challenge. The target categories for model detection were divided into the jacket, top, pants, skirt, and bag. According to the definition of inductive transfer learning, the purpose was to transfer the knowledge from the source domain to the target domain that could improve the effect of tasks in the target domain. Therefore, we used the two-phase training method to implement the transfer learning. Finally, the experimental results showed that the mAP of our model was better than the original YOLOv4 model through the two-phase transfer learning. The proposed model has multiple potential applications, such as an automatic labeling system, style retrieval, and similarity detection.

Sign in / Sign up

Export Citation Format

Share Document