Fast Temporal Video Segmentation Based on Krawtchouk-Tchebichef Moments

Abstract

With the increasing growth of multimedia data, the current real-world video sharing websites are being huge in repository size, more specifically video databases. This growth necessitates to look for superior techniques in processing video because video contains a lot of useful information. Temporal video segmentation (TVS) is considered essential stage in content-based video indexing and retrieval system. TVS aims to detect boundaries between successive video shots. TVS algorithm design is still challenging because most of the recent methods are unable to achieve fast and robust detection. In this regard, this paper proposes a TVS algorithm with high precision and recall values, and low computation cost for detecting different types of video transitions. The proposed algorithm is based on orthogonal moments which are considered as features to detect transitions. To increase the speed of the TVS algorithm as well as the accuracy, fast block processing and embedded orthogonal polynomial algorithms are utilized to extract features. This utilization will lead to extract multiple local features with low computational cost. Support vector machine (SVM) classifier is used to detect transitions. Specifically, the hard transitions are detected by the trained SVM model. The proposed algorithm has been evaluated on four datasets. In addition, the performance of the proposed algorithm is compared to several state-of-the-art TVS algorithms. Experimental results demonstrated that the proposed algorithm performance improvements in terms of recall, precision, and F1score are within the ranges (1.31 -2.58), (1.53 -4.28), and (1.41 -3.03), respectively. Moreover, the proposed method shows low computation cost which is 2% of real-time.

Multiple Object Tracking Using Edge Multi-Channel Gradient Model With ORB Feature

“…Andriyenko et al [25] formulate MOT as a continuous energy function minimization problem and find a strong local minimum by the conjugate gradient method to approximate the global optimal correlation solution. Recently, with the development of object detection and further research on visual object appearance, more attention has been paid to mining strong appearance characteristics which can be obtained by extracting features of objects [45,46,47] and establishing robust appearance similarity measurement in online MOT. Deep learning has been used as the appearance model of MOT [26,27], and compared with previous learning methods [28], it demonstrates better performance.…”

Video Shot Boundary Detection Based on Feature Fusion and Clustering Technique

“…In the application, feature detection and extraction usually can be divided into two directions based on processing compressed video domain and non-compressed video domain. The non-compressed domain method refers to the algorithms based on visual features, such as histogram [4] [9][10] [11] [12], pixel [13] [14] [15] [16], edge shape [17], motion [18] as well as orthogonal polynomial [19] [20] [21] [22]. While the compressed domain method refers to the algorithms based on compression coding, such as entropy coding including discrete cosine transform (DCT) and discrete Fourier transform (DFT) [12], macroblock coding [23], motion vector coding [24].…”

“…Dhiman et al [12] implement the detection of abrupt and gradual shot boundary according to DCT feature matching and histogram feature matching respectively. Abdulhussain et al [22] realize the video segmentation and shot boundary detection by calculating the similarity of orthogonal polynomial features.…”

Online Multiple Object Tracking Based on Open-Set Few-Shot Learning

“…Nowadays, many applications including self-driving vehicles [2], surveillance systems [3], and crowd analysis [4] require various video processing technologies such as person re-identification [5], video segmentation [6], [7] and efficient feature processing [8]. Multiple object tracking (MOT) [9] is one of the important problems for video analysis to estimate the states (or bounding boxes) of as many objects as possible in a video sequence.…”