Filters








430,541 Hits in 6.9 sec

Efficient object detection for high resolution images

Yongxi Lu, Tara Javidi
2015 2015 53rd Annual Allerton Conference on Communication, Control, and Computing (Allerton)  
In this paper we present effective methods to detect objects for high resolution images. We combine two complementary strategies.  ...  Current object proposal algorithms are computationally inefficient in processing high resolution images containing small objects, which makes them the bottleneck in object detection systems.  ...  ACKNOWLEDGMENT We would like to thank our collaborators Daphney-Stavroula Zois, Maxim Raginsky and Svetlana Lazebnik for useful discussions and suggestions.  ... 
doi:10.1109/allerton.2015.7447130 dblp:conf/allerton/LuJ15 fatcat:qnha7sxas5ebjht3pagwsswpqa

DISCRETE TOPOLOGY BASED HIERARCHICAL SEGMENTATION FOR EFFICIENT OBJECT-BASED IMAGE ANALYIS: APPLICATION TO OBJECT DETECTION IN HIGH RESOLUTION SATELLITE IMAGES

A. H. Syed, E. Saber, D. Messinger
2013 The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences  
Commission VI, WG VI/4 ABSTRACT: With rapid developments in satellite and sensor technologies, there has been a dramatic increase in the availability of high resolution (HR) remotely sensed images.  ...  The results of our representation are demonstrated both on a synthetic and a real high resolution images. Application of this representation to objectdetection is also discussed.  ...  ACKNOWLEDGEMENTS The authors would like to thank DigitalGlobe© for providing us with the high resolution images used in this paper, which were captured by the WorldView-2 Sensor.  ... 
doi:10.5194/isprsarchives-xl-1-w1-339-2013 fatcat:xausltt3zvf47prb7n337vzutq

Fast Efficient Object Detection Using Selective Attention [article]

Shivanthan Yohanandan, Andy Song, Adrian G. Dyer, Angela Faragasso, Subhrajit Roy, Dacheng Tao
2020 arXiv   pre-print
In contrast, most salience-guided object detection models typically employed high-resolution (e.g. 800 × 600 pixels [14] ) color images to train and run their detection models, which could explain their  ...  This suggests that high resolution images are not necessarily more accurate.  ... 
arXiv:1811.07502v3 fatcat:l4mj3yf4bjfmzenrovvycmz5g4

Optimized Collimator Designs for Small Animal SPECT Imaging With a Compact Gamma Camera

Yujin Qi
2005 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference  
The optimized collimator designs were obtained by maximizing the system detection efficiency for a given object resolution. The collimator designs were optimized for 140 keV incident gamma photons.  ...  The optimized collimator designs were obtained by maximizing the system detection efficiency for a given object resolution. The collimator designs were optimized for 140 keV incident gamma photons.  ...  Tsui from the Division of Medical Imaging Physics, Department of Radiology, Johns Hopkins University for his guidance and criticism on the collimator designs.  ... 
doi:10.1109/iembs.2005.1616792 pmid:17282561 fatcat:7lpddjy6nvcf5kacoq2u22qkfy

A Survey of Deep Learning-based Object Detection Methods and Datasets for Overhead Imagery

Junhyung Kang, Shahroz Tariq, Han Oh, Simon S. Woo
2022 IEEE Access  
We thank Jin Yong Park for reviewing the earlier version of the draft, and providing helpful and insightful comments.  ...  search area of images for efficient object detection.  ...  This process increases runtime efficiency by reducing the number of required high-resolution images.  ... 
doi:10.1109/access.2022.3149052 fatcat:iwvyg7qf6jgntgrwk4bmonrd5m

From Point to Region: Accurate and Efficient Hierarchical Small Object Detection in Low-Resolution Remote Sensing Images

Jingqian Wu, Shibiao Xu
2021 Remote Sensing  
To resolve this problem, we propose a Hierarchical Small Object Detection Network in low-resolution remote sensing images, named HSOD-Net.  ...  In comparison with the state-of-art models, HSOD-Net achieves remarkable precision in detecting small objects in low-resolution remote sensing images.  ...  However, in real-world settings, it is difficult to collect high-resolution images for the objects of interest.  ... 
doi:10.3390/rs13132620 fatcat:s5td3nguwvapzivjlpyz3oym3q

AutoFocus: Efficient Multi-Scale Inference [article]

Mahyar Najibi, Bharat Singh, Larry S. Davis
2019 arXiv   pre-print
This paper describes AutoFocus, an efficient multi-scale inference algorithm for deep-learning based object detectors.  ...  FocusPixels can be predicted with high recall, and in many cases, they only cover a small fraction of the entire image.  ...  The authors would also like to thank an Amazon Machine Learning gift for the AWS credits used for this research.  ... 
arXiv:1812.01600v2 fatcat:6ur56w4gvfbybk5kqnnnxa4xn4

Land Information Extraction with Boundary Preservation for High Resolution Satellite Image

Suresh Singh, Merugu Suresh, K. Jain
2015 International Journal of Computer Applications  
Object based techniques are used for the high resolution images but it is associated with the problem of proper segmentation.  ...  This paper includes efficient technique for edge detection to define land boundaries and feature selection technique for land information extraction.  ...  Earlier we were using pixel based techniques for all images to extract the information but in case of high resolution images pixel based techniques cannot be applied as two different objects may have same  ... 
doi:10.5120/21243-4014 fatcat:6u2buqwq3fhmxmovhgd5p5yory

Towards Efficient Video Detection Object Super-Resolution with Deep Fusion Network for Public Safety

Sheng Ren, Jianqi Li, Tianyi Tu, Yibo Peng, Jian Jiang, David Megías
2021 Security and Communication Networks  
In this paper, we proposed an efficient video detection object super-resolution with a deep fusion network for public security.  ...  Firstly, we designed a super-resolution framework for video detection objects.  ...  All the training and testing of the super-resolution model of the video detection object were completed on a high-performance server. is work was supported by the National Social Science Fund of China  ... 
doi:10.1155/2021/9999398 fatcat:uvsoflaltrdehgamgecbw7ex7q

Imaging techniques for the radioimmunodetection of cancer

F D Rollo, J A Patton
1980 Cancer Research  
As such, the imaging device utilized must have a high spatial resolution as well as high detection efficiency.  ...  These combined properties result in high detection of small lesions in cases where the object contrast is extremely low.  ...  The system provides high-resolution performance and high detection efficiency and is capable of resolving lesions having high object contrast.  ... 
pmid:7397700 fatcat:zepsikwrhrfa3gph4fhtbuet4q

Locate and Detect Persons in Crowded Scenes Aided by Objectiveness Measure

Shilin Zhang, Xunyuan Zhang
2015 International Journal of u- and e- Service, Science and Technology  
The other difficulty in pedestrian detection domain is the real time requirement, because the camera installed on the crossing road is in high definition.  ...  1024 images).  ...  3.1), as well as its binary approximation, i.e., binarized normed gradients feature (Section 3.3),for efficiently capturing the objective-ness of an image window.  ... 
doi:10.14257/ijunesst.2015.8.6.24 fatcat:upska6n5mjgjfipcidk6jj53dy

Addressing Visual Search in Open and Closed Set Settings [article]

Nathan Drenkow, Philippe Burlina, Neil Fendley, Onyekachi Odoemene, Jared Markowitz
2021 arXiv   pre-print
First, we present a method for predicting pixel-level objectness from a low resolution gist image, which we then use to select regions for performing object detection locally at high resolution.  ...  Searching for small objects in large images is a task that is both challenging for current deep learning systems and important in numerous real-world applications, such as remote sensing and medical imaging  ...  map to guide subsequent high-resolution object detection.  ... 
arXiv:2012.06509v2 fatcat:7prefb2evjegzpcrktcdh5cd2q

Small Object Detection in High-Resolution Images Based on Multiscale Detection and Re-training

GUANG-MIN SUN, JIA-YANG CHEN, BING LI, DONG YAN, YU LI, GANG XIE
2020 DEStech Transactions on Computer Science and Engineering  
Most of the current small object detection algorithms are designed for low-resolution images. They can neither directly process high-resolution images nor make full use of the information contained.  ...  Secondly, a corresponding low-resolution object detector is trained for each sub-task. Thirdly, the detectors are deployed to get detection results at different scales.  ...  The algorithm outperforms the single-scale detection framework in both accuracy and efficiency. Figure 1 . 1 Multiscale small object detection algorithm on high-resolution images.  ... 
doi:10.12783/dtcse/cmso2019/33598 fatcat:2rtkr2p3jnboxewwgtucq2hluq

Object Detection Algorithm for High Resolution Images Based on Convolutional Neural Network and Multiscale Processing

Rykhard Bohush, Sergey Ablameyko, Sviatlana Ihnatsyeva, Yahor Adamovskiy
2021 International Workshop on Computer Modeling and Intelligent Systems  
In this article we propose an effective algorithm for small object detection in high resolution images.  ...  Our algorithm shows better detecting small objects results in high-definition video than YOLOv4.  ...  We used a YOLOv4 CNN for object detection with an input layer size of [1024×1024]. It gives high efficiency in detecting small objects in 4K and 8К resolution images.  ... 
dblp:conf/cmis/BohushAIA21 fatcat:uk5cjzyddnfshm7s3m72suitpm

A object detection algorithm based on pyramid Convolutional Neural Networks (CNN) and feature map fusion model

Nu Wen, Biao He, Zhilu Yuan, Yong Fan
2019 Abstracts of the International Cartographic Association  
Meanwhile, in view of the shortcomings of the existing object detection algorithm to re-compress the image size, the image block and multi-threading technology are used to restore the original resolution  ...  high.  ...  Meanwhile, in view of the shortcomings of the existing object detection algorithm to re-compress the image size, the image block and multi-threading technology are used to restore the original resolution  ... 
doi:10.5194/ica-abs-1-399-2019 fatcat:7wc7atwxurdevaaopfskpt2ouu
« Previous Showing results 1 — 15 out of 430,541 results