Perspective Transformation Data Augmentation for Object Detection

Wang, Ke; Fang, Bin; Qian, Jiang; Yang, Su; Zhou, Xin; Zhou, Jie

doi:10.1109/access.2019.2962572

Cited by 32 publications

(22 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Data augmentation includes colour operations and geometric operations. Flipping, cropping, and rotation are most used augmentation techniques in object detection tasks [ 16 ]. Data augmentation is able to increase detection accuracy over +3.2 mAP on COCO dataset [ 21 ] (Figs.…”

Section: Methodsmentioning

confidence: 99%

New Zealand Shellfish Detection, Recognition and Counting: A Deep Learning Approach on Mobile Devices

Nguyen

Sun

2021

Communications in Computer and Information Science

View full text Add to dashboard Cite

New Zealand maintains excessive effort to organise the sustainable development of its marine resources, wildlife, and ecological environment. New Zealand has stringent rules to control fishing and to protect the continued growth of marine inhabitants. Fishing inspections, such as identifying and counting shellfish, are part of the daily routine of many New Zealand Fisheries officers. It is however considered labour-intensive and time-consuming work. This project, thus, develops a touch-less shellfish detection and counting web/mobile application on handheld devices using Mask R-CNN to assist New Zealand Fisheries officers in recognising and totalling shellfish automatically and accurately. New Zealand shellfish species are different from other places in the World. Thus, this study firstly investigates the best deep learning model to use for New Zealand shellfish recognition and detection. Selected shellfish dataset is collected from a local fish market in Auckland and trained by using the chosen artificial neural network. At last, a portable system is built to support Fisheries officers to count shellfish quickly and accurately. At this current stage, a web-based application has been successfully deployed at a local server (cvreact.aut.ac.nz) in which users can upload target objects to get results related to three major shellfish species including cockle, tuatua, and mussel. In the near future, this proposed model is scaled up to recognise more species to cover the popular shellfish species in New Zealand, thus benefiting the aquaculture as well.

show abstract

Section: Methodsmentioning

confidence: 99%

New Zealand Shellfish Detection, Recognition and Counting: A Deep Learning Approach on Mobile Devices

Nguyen

Sun

2021

Communications in Computer and Information Science

View full text Add to dashboard Cite

show abstract

“…c: PERSPECTIVE TRANSFORM From just one image, we can mimic various images taken for the same scene at different angles and positions using perspective transform [54]. The road scene frames are usually captured using camera attached to the top of the vehicle resulting in images with many off-lane information.…”

Section: B: Progressive Probabilistic Hough Transformmentioning

confidence: 99%

“…In order to get the target perspective of a warped image, it is needed to transform a trapezoid patch of the frontal road view into a rectangular image of the road from above. The trapezoid patch can be easily defined from the top, bottom, and side edges that all meet in the vanishing point [54]. By utilizing the vanishing point which we have estimated earlier in Equation ( 9), the needed edges can be known.…”

Section: B: Progressive Probabilistic Hough Transformmentioning

confidence: 99%

A Deep Learning-Based Benchmarking Framework for Lane Segmentation in the Complex and Dynamic Road Scenes

2021

View full text Add to dashboard Cite

Automatic lane detection is a classical task in autonomous vehicles that traditional computer vision techniques can perform. However, such techniques lack reliability for achieving high accuracy while maintaining adequate time complexity in the context of real-time detection in complex and dynamic road scenes. Deep neural networks have proved their ability to achieve competing accuracy and time complexity while training them on manually labeled data. Yet, the unavailability of segmentation masks for host lanes in harsh road environments hinders fully supervised methods' operability on such a problem. This work proposes integrating traditional computer vision techniques and deep learning methods to develop a reliable benchmarking framework for lane detection tasks in complex and dynamic road scenes. Firstly, an automatic segmentation algorithm based on a sequence of traditional computer vision techniques has been experimented. This algorithm precisely segments the semantic region of the host lane in the complex urban images of nuScenes dataset used in this framework; hence corresponding weak labels are generated. After that, the developed data is qualitatively evaluated to be used in training and benchmarking five state-of-the-art FCN-based architectures: SegNet, Modified SegNet, U-Net, ResUNet, and ResUNet++. The performance evaluation of the trained models is done visually and quantitatively by considering lane detection a binary semantic segmentation task. The output results show robust performance, especially ResUNet++, which outperforms all the other models while testing them in different complex road scenes with dynamic scenarios and various lighting conditions.

show abstract

“…There is a selfie image holding an identity card in this study, where there is a possibility of differences in holding an identity card. Therefore, it is necessary to augment data with perspective transformation techniques [19]. This technique will perform an image transformation, as shown in…”

Section: Building the Datasetsmentioning

confidence: 99%

“…The following process that is done is to do object detection using the Homography technique. Where to look for points with the same image features but with different perspectives, the perspective transformation process is carried out in the image [19].…”

Section: Oriented Fast and Rotated Brief (Orb) Feature Extractionmentioning

confidence: 99%

Implementation of Verification and Matching E-KTP with Faster R-CNN and ORB

Hudaya

Saadah

Irawan

2021

RESTI

View full text Add to dashboard Cite

needs a solid validation that has verification and matching uploaded images. To solve this problem, this paper implementing a detection model using Faster R-CNN and a matching method using ORB (Oriented FAST and Rotated BRIEF) and KNN-BFM (K-Nearest Neighbor Brute Force Matcher). The goal of the implementations is to reach both an 80% mark of accuracy and prove matching using ORB only can be a replaced OCR technique. The implementation accuracy results in the detection model reach mAP (Mean Average Precision) of 94%. But, the matching process only achieves an accuracy of 43,46%. The matching process using only image feature matching underperforms the previous OCR technique but improves processing time from 4510ms to 60m). Image matching accuracy has proven to increase by using a high-quality dan high quantity dataset, extracting features on the important area of EKTP card images.

show abstract

Perspective Transformation Data Augmentation for Object Detection

Cited by 32 publications

References 22 publications

New Zealand Shellfish Detection, Recognition and Counting: A Deep Learning Approach on Mobile Devices

New Zealand Shellfish Detection, Recognition and Counting: A Deep Learning Approach on Mobile Devices

A Deep Learning-Based Benchmarking Framework for Lane Segmentation in the Complex and Dynamic Road Scenes

Implementation of Verification and Matching E-KTP with Faster R-CNN and ORB

Contact Info

Product

Resources

About