2019 International Conference on Image and Vision Computing New Zealand (IVCNZ)最新文献_第2页

Deep Learning for Pollen Sac Detection and Measurement on Honeybee Monitoring Video 基于深度学习的蜜蜂监控视频花粉囊检测与测量

2019 International Conference on Image and Vision Computing New Zealand (IVCNZ) Pub Date : 2019-12-01 DOI: 10.1109/IVCNZ48456.2019.8961011

Cheng Yang, J. Collins

{"title":"Deep Learning for Pollen Sac Detection and Measurement on Honeybee Monitoring Video","authors":"Cheng Yang, J. Collins","doi":"10.1109/IVCNZ48456.2019.8961011","DOIUrl":"https://doi.org/10.1109/IVCNZ48456.2019.8961011","url":null,"abstract":"This paper introduces a new model which applies deep learning techniques to pollen sac detection and measurement on honeybee monitoring video. The outcome of this model is a measurement of the number of pollen sacs being brought to the beehive, so that beekeepers will not need to open beehives frequently to check food storage. The pollen sacs are detected on individual bee images which are collected using a bee detection model on the entire video frame. The pollen detection model is built using a deep convolutional neural network. The architecture is Faster RCNN with VGG-16 core network. The network is trained to detect pollen sacs so the individual bee images are identified as either pollen or nonpollen bee images. This pollen sac detection model is then combined with a bee tracking model, so that each flying bee tracked on successive video frames is identified as carrying pollen or not. Finally, the number of pollen-carrying bees can be counted. The experimental results show that the measurement error of this model is 7%. The deep learning model improves the results from the conventional image processing method, which produced 33% measurement error.","PeriodicalId":217359,"journal":{"name":"2019 International Conference on Image and Vision Computing New Zealand (IVCNZ)","volume":"95 37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129222814","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 13

Fingertips Detection in Egocentric Video Frames using Deep Neural Networks 基于深度神经网络的自中心视频帧指尖检测

2019 International Conference on Image and Vision Computing New Zealand (IVCNZ) Pub Date : 2019-12-01 DOI: 10.1109/IVCNZ48456.2019.8960957

Purnendu Mishra, K. Sarawadekar

{"title":"Fingertips Detection in Egocentric Video Frames using Deep Neural Networks","authors":"Purnendu Mishra, K. Sarawadekar","doi":"10.1109/IVCNZ48456.2019.8960957","DOIUrl":"https://doi.org/10.1109/IVCNZ48456.2019.8960957","url":null,"abstract":"In recent years, there has been much advancement in Augmented Reality technologies. Also, there has been a rise in the usage of wearable cameras. These technologies allow us to interact with the virtual world and the real world simultaneously. Hand gestures or finger gestures can be used to provide input instructions replacing conventional tools like a keyboard or a mouse. This paper introduces an improvement over the YOLSE (You Only Look what You Should See) model towards multiple fingertip position estimation. We propose a regression-based technique to locate fingertip(s) in a multi-gesture condition. First, the hand gesture is segmented from the scene using a deep neural network (DNN) based object detection model. Next, fingertip(s) positions are estimated using MobileNetv2 architecture. It is difficult to use direct regression when the varying number of visible fingertips are present in different egocentric hand gestures. We used the multi-label classification concept to identify all the visible extended fingers in the image. Average errors on RGB image with a resolution of 640 × 480 is 6.1527 pixels. The processing time of 9.072 ms is achieved on Nvidia GeForce GTX 1080 GPU.","PeriodicalId":217359,"journal":{"name":"2019 International Conference on Image and Vision Computing New Zealand (IVCNZ)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125365317","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 5

Generalization Approach for CNN-based Object Detection in Unconstrained Outdoor Environments 无约束室外环境下基于cnn的目标检测泛化方法

2019 International Conference on Image and Vision Computing New Zealand (IVCNZ) Pub Date : 2019-12-01 DOI: 10.1109/IVCNZ48456.2019.8960992

Hedi Hedayati, B. McGuinness, M. Cree, J. Perrone

引用次数: 1

Coniferous Trees Needles-Based Taxonomy Classification 针叶树的分类与分类

2019 International Conference on Image and Vision Computing New Zealand (IVCNZ) Pub Date : 2019-12-01 DOI: 10.1109/IVCNZ48456.2019.8961023

M. Haindl, Pavel Zid

引用次数: 0

Pedestrian Proximity Detection using RGB-D Data 基于RGB-D数据的行人接近检测

2019 International Conference on Image and Vision Computing New Zealand (IVCNZ) Pub Date : 2019-12-01 DOI: 10.1109/IVCNZ48456.2019.8961013

Adam Tupper, R. Green

引用次数: 3

Recognizing Text with a CNN 用CNN识别文本

2019 International Conference on Image and Vision Computing New Zealand (IVCNZ) Pub Date : 2019-12-01 DOI: 10.1109/IVCNZ48456.2019.8961031

Kulsoom Mansoor, C. Olson

引用次数: 1

Adaptation of Bidirectional Kalman Filter to Multi-Frequency Time-of-Flight Range Imaging 双向卡尔曼滤波在多频飞行时间距离成像中的自适应

2019 International Conference on Image and Vision Computing New Zealand (IVCNZ) Pub Date : 2019-12-01 DOI: 10.1109/IVCNZ48456.2019.8960962

A. Alqassab, L. Streeter, M. Cree, Carl A. Lickfold, V. Farrow, S. Lim

引用次数: 0

Minutiae Triangle Graphs: A New Fingerprint Representation with Invariance Properties 细部三角形图:一种新的具有不变性的指纹表示

2019 International Conference on Image and Vision Computing New Zealand (IVCNZ) Pub Date : 2019-12-01 DOI: 10.1109/IVCNZ48456.2019.8960988

Akmal-Jahan Mohamed-Abdul-Cader, Watcharapong Chaidee, Jasmine Banks, V. Chandran

{"title":"Minutiae Triangle Graphs: A New Fingerprint Representation with Invariance Properties","authors":"Akmal-Jahan Mohamed-Abdul-Cader, Watcharapong Chaidee, Jasmine Banks, V. Chandran","doi":"10.1109/IVCNZ48456.2019.8960988","DOIUrl":"https://doi.org/10.1109/IVCNZ48456.2019.8960988","url":null,"abstract":"A new algorithm for matching finger or palm prints is presented for use where the full hand is considered as a biometric and only parts may be available in images for comparison. The algorithm uses an extended version of the minutiae-based approach treating the pattern as a graph of minutiae-like points. The procedure to identify minutiae-like points uses Gabor filtering, edge detection and thinning and following line patterns. A set of such points is subjected to Delaunay triangulation yielding a starting set of base-triangles for matching. There can be multiple matches of such triangles between the template and test - as similar triangles with a tolerance in the angles. Graphs are then grown to 5 and more nodes as long as a match can be found, until the maximum size matching graph is obtained. If the test matches a significant part of the template, the maximum order of graph matched will be high. The matching process is robust to transformations such as rotation, translation and scale changes. It can be applied to any part of the hand provided minutiae-like points are identifiable prior to the matching steps. The algorithm is tested using 158 fingerprint images from FVC 2002 DB1. 100 genuine and 5048 impostor scores are generated from 46 templates and 112 testing images. It had an EER of about 6%. It proves the principle behind the methodology and demonstrates that the method can be effective with degraded fingerprint images and is robust to similarity transformations present in the data. It can be applied for forensic fingerprint matching from the palm or parts other than the fingertips. By using multiple parts and multiple templates, the accuracy of the method will be improved with fusion in future versions of the algorithm.","PeriodicalId":217359,"journal":{"name":"2019 International Conference on Image and Vision Computing New Zealand (IVCNZ)","volume":"123 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132090189","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Use of Moiré Patterns in Camera Position Estimation 在相机位置估计中的应用

2019 International Conference on Image and Vision Computing New Zealand (IVCNZ) Pub Date : 2019-12-01 DOI: 10.1109/IVCNZ48456.2019.8961010

Samuel Banks, R. Green, Jun Junghyun

引用次数: 4

Image Correction with Curvature and Geometric Wavefront Sensors in Simulation and On-sky 曲率和几何波前传感器在仿真和天空中的图像校正

2019 International Conference on Image and Vision Computing New Zealand (IVCNZ) Pub Date : 2019-12-01 DOI: 10.1109/IVCNZ48456.2019.8961022

Sierra Hickman, S. Weddell, R. Clare

引用次数: 5