Muhammad Aamir¹, Ziaur Rahman^1,*, Waheed Ahmed Abro², Uzair Aslam Bhatti³, Zaheer Ahmed Dayo¹, Muhammad Ishfaq¹

CMC-Computers, Materials & Continua, Vol.75, No.3, pp. 6351-6373, 2023, DOI:10.32604/cmc.2023.038173

Abstract Object detection in images has been identified as a critical area of research in computer vision image processing. Research has developed several novel methods for determining an object’s location and category from an image. However, there is still room for improvement in terms of detection efficiency. This study aims to develop a technique for detecting objects in images. To enhance overall detection performance, we considered object detection a two-fold problem, including localization and classification. The proposed method generates class-independent, high-quality, and precise proposals using an agglomerative clustering technique. We then combine these proposals with the relevant input image to train… More >

Changgeng Shuai^{1, 2}, Shike Zhang^{1, 2}, Jiaxuan Yang^{1, 2}, Sitong Zhou^{1, 2}

Sound & Vibration, Vol.52, No.4, pp. 2-5, 2018, DOI:10.32604/sv.2018.03724

Abstract Advanced array processing approaches require accurate knowledge of the location of individual element in a sensor array. Most array shape estimation methods require the directions of sources. In this paper, an array shape estimation method based on eigen-decomposition is presented. The directions of sources do not need to be considered in advance and optimal array shape is generated through a series of iterations. To further improve the accuracy of this algorithm, a partitioned eigenstructure method is introduced. Numerical simulations using non-partitioned and partitioned method are conducted to verify the performance of the proposed technique. More >