8757

A Fast and Accurate GHT Implementation on CUDA

Nikhil Jotwani, Sudhakar Sah
Center for Research in Engr Sciences and Technology-CREST, KPIT Cummins Infosystems Ltd., Pune, India
ICOMEC, 2011

@article{jotwani2011fast,

   title={A Fast and Accurate GHT Implementation on CUDA},

   author={Jotwani, N. and Sah, S.},

   year={2011}

}

Download Download (PDF)   View View   Source Source   

697

views

Generalized Hough Transform (GHT) is a well known but seldom used algorithm for object detection. The merit of this algorithm is its ability to detect object location and its pose accurately. However, this algorithm has a huge drawback of high memory and extensive computational requirement. As a result, usage of this algorithm for object detection is limited. In this paper, we are proposing the parallel implementation of GHT algorithm on GPU (Graphical Processing Unit) that is 80 times faster compared to its CPU (Central Processing Unit) version. We have also achieved comparable speed up with some of the best GHT implementations on GPU for limited number of poses. However, our parallel design performs better for large number of poses. The uniqueness of our parallel design is that the performance does not get affected by increasing number of poses. Increased number of poses identification at the same performance increases the resolution of scale and rotation that can be detected.
VN:F [1.9.22_1171]
Rating: 0.0/5 (0 votes cast)

* * *

* * *

TwitterAPIExchange Object
(
    [oauth_access_token:TwitterAPIExchange:private] => 301967669-yDz6MrfyJFFsH1DVvrw5Xb9phx2d0DSOFuLehBGh
    [oauth_access_token_secret:TwitterAPIExchange:private] => o29ji3VLVmB6jASMqY8G7QZDCrdFmoTvCDNNUlb7s
    [consumer_key:TwitterAPIExchange:private] => TdQb63pho0ak9VevwMWpEgXAE
    [consumer_secret:TwitterAPIExchange:private] => Uq4rWz7nUnH1y6ab6uQ9xMk0KLcDrmckneEMdlq6G5E0jlQCFx
    [postfields:TwitterAPIExchange:private] => 
    [getfield:TwitterAPIExchange:private] => ?cursor=-1&screen_name=hgpu&skip_status=true&include_user_entities=false
    [oauth:protected] => Array
        (
            [oauth_consumer_key] => TdQb63pho0ak9VevwMWpEgXAE
            [oauth_nonce] => 1481283131
            [oauth_signature_method] => HMAC-SHA1
            [oauth_token] => 301967669-yDz6MrfyJFFsH1DVvrw5Xb9phx2d0DSOFuLehBGh
            [oauth_timestamp] => 1481283131
            [oauth_version] => 1.0
            [cursor] => -1
            [screen_name] => hgpu
            [skip_status] => true
            [include_user_entities] => false
            [oauth_signature] => 8pW48CFxaKH9L1RoJQ1UahbpbLc=
        )

    [url] => https://api.twitter.com/1.1/users/show.json
)
Follow us on Facebook
Follow us on Twitter

HGPU group

2081 peoples are following HGPU @twitter

HGPU group © 2010-2016 hgpu.org

All rights belong to the respective authors

Contact us: