Hareketli hedef takip sisteminde genelleştirilmiş Hough dönüşümü (GHT) ve normalleştirilmiş çapraz ilinti (NCC) yöntemlerini ardışıl kullanarak eşleşme doğruluğunun arttırılması
Öz
Bu çalışmada; hedefin daha iyi tahmin
edilmesinde, hedefin ve şablon piksellerinin yoğunlukları arasında ilinti puanı
hesaplanmıştır. Görünüm değişikliklerini ele almak için yapılan işlemde,
hedefin şablonları 12 değişik görünüşten alınmıştır. Resmin merkez noktası ile
sınırlayıcı kutunun merkez noktası arasındaki mesafe hesaplanmış ve bir hata
sinyali olarak dönüştürülmüştür. Hata sinyalini kullanarak servo motorlar
hedefin merkezileştirilmesi için kameranın görüş açısını değiştirmeye
yönlendirilmiştir. Böylece hedef, değişen bir geçmişe sahip gerçek zamanlı
olarak tanınmış ve izlenmiştir.
Anahtar Kelimeler
Görüntü işleme Kenar algılama Genelleştirilmiş Hough dönüşümü Normalleştirilmiş çapraz ilinti
Kaynakça
- Referans1 Boris Babenko, M-H Yang, Serge Belongie, “Robust Object Tracking with Online Multiple Instance Learning”, IEEE Transactions On Pattern Analysis and Machine Intelligence, Vol. 33, No. 8, pp. 1619-1632, August 2011.
- Referans2 Yung-Chi Lo, Po-Yen Lee, and Shyi-Chyi Cheng, “Space-Time Template Matching For Human Action Detection Using Volume-Based Generalized Hough Transform”, 18th IEEE International Conference on Image Processing, 2011.
- Referans3 Yonghui Hu, Wei Zhoo, Long Wang, “Vision-Based Target Tracking and Collision Avoidance for Two Autonomous Robotic Fish”, IEEE Transactions On Industrial Electronics, Vol. 56, No. 5, pp. 1401-1410, May 2009.
- Referans4 Jay Hyuk Choi, Wonsuk Lee, Hyochoong Bang, “Helicopter Guidance for Vision-based Tracking and Landing on a Moving Ground Target”, 2011 11th International Conference on Control, Automation and Systems, Oct. 26-29, 2011 in KINTEX, Gyeonggi-do, Korea
- Referans5 Michael D. Breitenstein, “Robust Tracking-by-Detection using a Detector Confidence Particle Filter”, 2009 IEEE 12th International Conference on Computer Vision (ICCV).
- Referans6 Mustafa ÖZDEN and Ediz POLAT, “Mean–Shift ve Kernel Yoğunluk Tahmini Ile Görüntülerde Nesne Takibi”, ASYU-INISTA 2004 Ak.ll. Sistemlerde Yenilikler ve Uygulamalar Sempozyumu, Yıldız Teknik Üniversitesi Elektrik-Elektronik Fakultesi.
- Referans7 Alper Yılmaz, “Object Tracking by Asymmetric Kernel Mean Shift with Automatic Scale and Orientation Selection”, IEEE Conference on Computer Vision and Pattern Recognition, June 2007.
- Referans8 Alan J. Lipton, Hironobu Fujiyoski, Raju S. Patil, “Moving Target Classification and Tracking from Real-time Video”, 0-8186-8606-5/98/, IEEE.
- Referans9 John Canny, “A Computational Approach to Edge Detection”, IEEE Transactions On Pattern Analysis and Machine Intelligence, Vol. PAMI-8, No. 6, November 1986.
- Referans10 D. Marr ve E. Hildreth, “Theory of Edge Detection”, Proceedings of the Royal Society of London. Series B, Biological Sciences, Vol. 207, No. 1167.(Feb. 29, 1980).
- Referans11 D. H. Ballard, “Generalizing The Hough Transform To Detect Arbitrary Shapes”, Pattern Recognition, Vol. 11, No.2, 1981.
- Referans12 http://fourier.eng.hmc.edu/e161/lectures/hough/node6.html, Nisan 2013.
- Referans13 D. M. Tsai and C. T. Lin, “Fast Normalized Cross Correlation For Defect Detection”, Pattern Recognition, Volume 24, No. 15, November 2003.
- Referans14 Wikipedia internet sitesi, http://en.wikipedia.org/wiki/Cross-correlation, Nisan 2013.
- Referans15 Vision Concepts Dokümanı, National Instruments Corporation.
Improving accuracy matching in a mobile target tracking system by using consecutively generalized Hough transform (GHT) and normalized cross correlation (NCC) methods
Öz
In this study; together with this to make a
better estimation of the target, correlation score is also computed between the
intensities of the target and the template pixels. In the application in order
to handle the appearance changes, the templates of the target are taken from 12
different appearances. The matches taking a score over defined level are
considered as real matches and bounded by a bounding box. Using the error
signal, servomotors are controlled to change the point of view of the camera to
centralize the target. In this way the target recognized and tracked near real
time with a changing background.
Anahtar Kelimeler
image processing edge detection generalized Hough transform normalized cross correlation
Kaynakça
- Referans1 Boris Babenko, M-H Yang, Serge Belongie, “Robust Object Tracking with Online Multiple Instance Learning”, IEEE Transactions On Pattern Analysis and Machine Intelligence, Vol. 33, No. 8, pp. 1619-1632, August 2011.
- Referans2 Yung-Chi Lo, Po-Yen Lee, and Shyi-Chyi Cheng, “Space-Time Template Matching For Human Action Detection Using Volume-Based Generalized Hough Transform”, 18th IEEE International Conference on Image Processing, 2011.
- Referans3 Yonghui Hu, Wei Zhoo, Long Wang, “Vision-Based Target Tracking and Collision Avoidance for Two Autonomous Robotic Fish”, IEEE Transactions On Industrial Electronics, Vol. 56, No. 5, pp. 1401-1410, May 2009.
- Referans4 Jay Hyuk Choi, Wonsuk Lee, Hyochoong Bang, “Helicopter Guidance for Vision-based Tracking and Landing on a Moving Ground Target”, 2011 11th International Conference on Control, Automation and Systems, Oct. 26-29, 2011 in KINTEX, Gyeonggi-do, Korea
- Referans5 Michael D. Breitenstein, “Robust Tracking-by-Detection using a Detector Confidence Particle Filter”, 2009 IEEE 12th International Conference on Computer Vision (ICCV).
- Referans6 Mustafa ÖZDEN and Ediz POLAT, “Mean–Shift ve Kernel Yoğunluk Tahmini Ile Görüntülerde Nesne Takibi”, ASYU-INISTA 2004 Ak.ll. Sistemlerde Yenilikler ve Uygulamalar Sempozyumu, Yıldız Teknik Üniversitesi Elektrik-Elektronik Fakultesi.
- Referans7 Alper Yılmaz, “Object Tracking by Asymmetric Kernel Mean Shift with Automatic Scale and Orientation Selection”, IEEE Conference on Computer Vision and Pattern Recognition, June 2007.
- Referans8 Alan J. Lipton, Hironobu Fujiyoski, Raju S. Patil, “Moving Target Classification and Tracking from Real-time Video”, 0-8186-8606-5/98/, IEEE.
- Referans9 John Canny, “A Computational Approach to Edge Detection”, IEEE Transactions On Pattern Analysis and Machine Intelligence, Vol. PAMI-8, No. 6, November 1986.
- Referans10 D. Marr ve E. Hildreth, “Theory of Edge Detection”, Proceedings of the Royal Society of London. Series B, Biological Sciences, Vol. 207, No. 1167.(Feb. 29, 1980).
- Referans11 D. H. Ballard, “Generalizing The Hough Transform To Detect Arbitrary Shapes”, Pattern Recognition, Vol. 11, No.2, 1981.
- Referans12 http://fourier.eng.hmc.edu/e161/lectures/hough/node6.html, Nisan 2013.
- Referans13 D. M. Tsai and C. T. Lin, “Fast Normalized Cross Correlation For Defect Detection”, Pattern Recognition, Volume 24, No. 15, November 2003.
- Referans14 Wikipedia internet sitesi, http://en.wikipedia.org/wiki/Cross-correlation, Nisan 2013.
- Referans15 Vision Concepts Dokümanı, National Instruments Corporation.
Ayrıntılar
| Konular | Elektrik Mühendisliği |
|---|---|
| Bölüm | Araştırma Makalesi |
| Yazarlar | |
| Yayımlanma Tarihi | 1 Şubat 2018 |
| Gönderilme Tarihi | 8 Mayıs 2017 |
| Kabul Tarihi | 1 Şubat 2018 |
| Yayımlandığı Sayı | Yıl 2018 Cilt: 22 Sayı: 1 |
Kaynak Göster
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.