Integration of Projection Histograms and Linear Prediction for Object Tracking
DOI:
https://doi.org/10.11113/jt.v39.462Abstract
Kertas kerja ini mengemukakan satu sistem visual untuk menjejak objek bergerak yang dapat beroperasi secara masa–nyata, efisien dan tahan lasak, dengan menggunakan turutan imej yang diperolehi daripada satu kamera statik. Algoritma menjejak yang dikemukakan menggabungkan teknik Unjuran Histogram dan kaedah Ramalan Linar untuk mencapai kelajuan menjejak yang lebih tinggi. Unjuran Histogram dilakukan untuk mendapatkan lokasi sebenar bagi objek yang dijejak, manakala kaedah Ramalan Linar disertakan dalam algoritma menjejak yang dikemukakan untuk meramal lokasi bagi objek bergerak dalam imej seterusnya, berdasarkan beberapa ukuran centroid sebelumnya. Hasil gabungan teknik Unjuran Histogram dan tertib kedua Ramalan Linar telah membolehkan algoritma yang dikemukakan untuk menjejak objek bergerak dengan tepat. Potensi and kecekapan bagi algoritma menjejak yang dikemukakan telah dibuktikan oleh keputusan menjejak yang baik pada beberapa turutan imej eksperimen. Kata kunci: menjejak pergerakan, Unjuran Histogram, Ramalan Linar, perbezaan bingkai In this paper, a real–time, efficient and robust visual tracking system for a single moving object using image sequences captured by a stationary camera is presented. The proposed tracking algorithm integrates the Projection Histograms technique with the Linear Prediction method in order to achieve a faster tracking speed. The Projection Histograms technique is applied to obtain the actual location of the tracked target, whereas the Linear Prediction method is incorporated in the proposed tracking algorithm to predict the location of the moving object in the next frame based on its several past centroid measurements. The Projection Histograms technique coupled with a second order Linear Prediction method has enabled the proposed algorithm to accurately track a single moving object. The potential applicability and efficiency of the proposed tracking algorithm has been validated by good tracking results on several experimental image sequences. Key words: Motion tracking, projection histograms, linear prediction, frame differencingDownloads
Published
2012-01-20
Issue
Section
Science and Engineering
License
Copyright of articles that appear in Jurnal Teknologi belongs exclusively to Penerbit Universiti Teknologi Malaysia (Penerbit UTM Press). This copyright covers the rights to reproduce the article, including reprints, electronic reproductions, or any other reproductions of similar nature.
How to Cite
Integration of Projection Histograms and Linear Prediction for Object Tracking. (2012). Jurnal Teknologi (Sciences & Engineering), 39(1), 57–68. https://doi.org/10.11113/jt.v39.462