Shot Detection Algorithm Research Articles

Event detection in football: Improving the reliability of match analysis.

With recent technological advancements, quantitative analysis has become an increasingly important area within professional sports. However, the manual process of collecting data on relevant match events like passes, goals and tacklings comes with considerable costs and limited consistency across providers, affecting both research and practice. In football, while automatic detection of events from positional data of the players and the ball could alleviate these issues, it is not entirely clear what accuracy current state-of-the-art methods realistically achieve because there is a lack of high-quality validations on realistic and diverse data sets. This paper adds context to existing research by validating a two-step rule-based pass and shot detection algorithm on four different data sets using a comprehensive validation routine that accounts for the temporal, hierarchical and imbalanced nature of the task. Our evaluation shows that pass and shot detection performance is highly dependent on the specifics of the data set. In accordance with previous studies, we achieve F-scores of up to 0.92 for passes, but only when there is an inherent dependency between event and positional data. We find a significantly lower accuracy with F-scores of 0.71 for passes and 0.65 for shots if event and positional data are independent. This result, together with a critical evaluation of existing methodologies, suggests that the accuracy of current football event detection algorithms operating on positional data is currently overestimated. Further analysis reveals that the temporal extraction of passes and shots from positional data poses the main challenge for rule-based approaches. Our results further indicate that the classification of plays into shots and passes is a relatively straightforward task, achieving F-scores between 0.83 to 0.91 ro rule-based classifiers and up to 0.95 for machine learning classifiers. We show that there exist simple classifiers that accurately differentiate shots from passes in different data sets using a low number of human-understandable rules. Operating on basic spatial features, our classifiers provide a simple, objective event definition that can be used as a foundation for more reliable event-based match analysis.

Tomato fruit disease detection based on improved single shot detection algorithm

Tomato fruit disease detection based on improved single shot detection algorithm

Server node video processing based on feature depth analysis algorithm

ABSTRACT The complex and diverse server video data leads to the problem of effective retrieval of these data. The current shot edge detection algorithm and key frame extraction algorithm in server node video processing have problems such as poor extraction performance and poor adaptability. Therefore, the research combined the feature depth analysis to improve the two, and the performance was verified by experiments. The shot detection algorithm is verified by modifying the secondary detection model. This method can detect lens mutation, gradual change and other phenomena well, and the accuracy rate can reach 99.7%. The precision under the gradient lens is 92.08%, far higher than 63.50% and 85.39% of ISIFT and CS-DFS. In the verification experiment using Convolution Neural Networks (CNNs) key frame extraction algorithm, the number of key frame extractions of the proposed algorithm can reach up to 88 frames. Compared with other methods, the accuracy of the algorithm studied can reach 99.67%, which is higher than the comparison algorithm. In general, the improved algorithm proposed in the study has high adaptability to edge detection and the ability to express key frame video, and has high practicability in actual server node video processing.

Artificial Intelligence System for Effective Detection of Animal Intervention in Croplands

Abstract: Animal intervention is significant intimidation to the potency of the crops, which influences food security and decreases the value to the farmers. This suggested model displays the growth of the Internet of Things and Machine learning technique-based resolutions to surmount this obstacle. Raspberry Pi commands the machine algorithm, which is interfaced with the ESP8266 Wireless Fidelity module, Pi-Camera, Speaker/Buzzer, and LED. Machine learning algorithms similar to Regionbased Convolutional Neural Network and Single Shot Detection technology represents an essential function to identify the target in the pictures and classify the creatures. The experimentation exhibits that the Single Shot Detection algorithm exceeds than Region-based Convolutional Neural Network algorithm. Ultimately, the Twilio API interfaced software decimates the data to the farmers to take conclusive work in their farm territory. Keywords: Region-Based Convolutional Neural Network (R-CNN), Tensor Flow, Raspberry Pi, Internet of Things (IoT), Single Shot Detector (SSD)

Application of IOT and machine learning in crop protection against animal intrusion

Animal intrusion is a major threat to the productivity of the crops, which affects food security and reduces the profit to the farmers. This proposed model presents the development of the Internet of Things and Machine learning technique-based solutions to overcome this problem. Raspberry Pi runs the machine algorithm, which is interfaced with the ESP8266 Wireless Fidelity module, Pi Camera, Buzzer, and LED. Machine learning algorithms like Region-based Convolutional Neural Network and Single Shot Detection technology plays an important role to detect the object in the images and classify the animals. The experimentation reveals that the Single Shot Detection algorithm outperforms than Region-based Convolutional Neural Network algorithm. Finally, the Twilio API interfaced software decimates the information to the farmers to take decisive action in their farm field.

Movie Tags Prediction and Segmentation Using Deep Learning

The sheer volume of movies generated these days requires an automated analytics for efficient classification, query-based search, and extraction of desired information. These tasks can only be efficiently performed by a machine learning based algorithm. We address the same issue in this paper by proposing a deep learning based technique for predicting the relevant tags for a movie and segmenting the movie with respect to the predicted tags. We construct a tag vocabulary and create the corresponding dataset in order to train a deep learning model. Subsequently, we propose an efficient shot detection algorithm to find the key frames in the movie. The extracted key frames are analyzed by the deep learning model to predict the top three tags for each frame. The tags are then assigned weighted scores and are filtered to generate a compact set of most relevant tags. This process also generates a corpus which is further used to segment a movie based on a selected tag. We present a rigorous analysis of the segmentation quality with respect to the number of tags selected for the segmentation. Our detailed experiments demonstrate that the proposed technique is not only efficacious in predicting the most relevant tags for a movie, but also in segmenting the movie with respect to the selected tags with a high accuracy.

Video genre identification using clustering-based shot detection algorithm

Rapid growth in storage technology and data acquisition has significantly increased the volume of multimedia data online. A challenging problem is to analyze that multimedia data which are in massive quantity. In recent years, indexing of video files based on contents has gained increased popularity in research community. There are also attempts at identifying if a video clip is containing a specific genre of video, e.g., an sports video, movie, drama, animation or talk show. These proposed techniques, however, use a long list of audio visual features in achieving this classification task, which obviously decreases processing efficiency. Based on certain patterns in audio visual features and basic grammar of talk show, this research differentiates multimedia contents of talk shows from rest of the video genres. Our multimodal rule-based classification approach exploits shots and scenes in a video as classification features. The contents from popular multimedia databases like DailyMotion, YouTube and movies from Hollywood and Bollywood are used as dataset to test overall system of genre identification. The system achieves precision and recall of 98% and 100%, respectively, on 600 selected videos of more than 600 h of duration to classify multimedia content as either ‘TalkShow’ or ‘OtherVideo’ category.

A shot detection technique using linear regression of shot transition pattern

Video segmentation acts as the fundamental step for various applications like, archiving, content based retrieval, copy detection and summarization of video data. Shot detection is first level of segmentation. In this work, a shot detection methodology is presented that evolves around a simple shot transition model based on the similarity of the frames with respect to a reference frame. Frames in an individual shot are very similar in terms of their visual content. Whenever a shot transition occurs a change in similarity values appears. For an abrupt transition, the rate of change is very high, while for gradual it is not so apparent. To overcome the effect of noise in similarity values, line is fit over a small window using a linear regression. Thus slope of this line exhibits the underlying pattern of transition. A novel algorithm for shot detection, hence, is developed based on the variation pattern of the similarity values of the frames with respect to a reference frame. First an algorithm is proposed, which is direct descendant of the underlying transition model and applies a threshold on the similarity values to detect the transitions. Then this algorithm is improved by utilizing the slope of linear approximation of variation in similarity values rather than the absolute values, following least square regression. Threshold on the slope is determined with a bias towards minimizing false rejection rate at the cost of false acceptance rate. Finally, a simple post-processing technique is adopted to reduce the false detection. Experiment is done with the video sequences taken from TRECVID 2001 database, action type movie video, recorded sports and news video. Comparison with few other systems indicates that the performance of the proposed scheme is quite satisfactory.

Design and Implementation of Video Shot Detection on Field Programmable Gate Arrays

Video has become an interactive medium of communication in everyday life. The sheer volume of video makes it extremely difficult to browse through and find the required data. Hence extraction of key frames from the video which represents the abstract of the entire video becomes necessary. The aim of the video shot detection is to find the position of the shot boundaries, so that key frames can be selected from each shot for subsequent processing such as video summarization, indexing etc. For most of the surveillance applications like video summery, face recognition etc., the hardware (real time) implementation of these algorithms becomes necessary. Here in this paper we present the architecture for simultaneous accessing of consecutive frames, which are then used for the implementation of various Video Shot Detection algorithms. We also present the real time implementation of three video shot detection algorithms using the above mentioned architecture on FPGA (Field Programmable Gate Arrays).

A Novel Approach for Tracking with Implicit Video Shot Detection

Video shot detection - Shot change detection is an essential step in video content analysis. The field of Video Shot Detection (VSD) is a well exploited area. In the past, there have been numerous approaches designed to successfully detect shot boundaries for temporal segmentation. Robust Pixel Based Method is used to detect shot changes in a video sequence. Tracking algorithm is a time consuming process due to the large amount of data contained in video using the video shot detection the computational cost can be reduced to a great extent by the discarding the frames which are not of any interest for the tracking algorithm. In this paper we present a novel approach of combining the concepts of Video shot detection and Object tracking using particle filter to give us a efficient Tracking algorithm with implicit shot detection. Keywords - Bhattacharyya distance, Local adaptive threshold, Particle filter, Robust Pixel Difference method, Residual Re-sampling, Shot detection. I. INTRODUCTION The rapid development of storage and multimedia technologies has made the retrieval and processing of videos relatively easy. Temporal segmentation is a fundamental step in video processing, and shot change detection is the most basic way to achieve it. However, while hard cuts (abrupt transitions) can be easily detected by finding changes in a color histogram, gradual transitions such as dissolves, fades, and wipes are hard to locate. In practice, however, 99% of all edits fall into one of the following four categories hard cuts, fades, wipes and dissolves. Many shot change detection studies focus on finding low-level visual features, e.g., color histograms and edges, and then locate the spots of changes in those features. We focus on using Robust Pixel Method for shot detection. The conventional shot detection method using pixel wise comparison is not very efficient since it doesn't provide noise tolerance and because of its global thresholding nature. Many scenes involving sudden illumination changes such as lighting etc false trigger a shot change in the conventional method. The robust pixel method used in this paper provides threshold for noise and also locally adaptive threshold which makes it effective in situations where the conventional method fails. Object tracking is an important task in the field of computer vision. It generates the path traced by a specified object by locating its position in each frame of the video sequence. The use of Object tracking is pertinent in many vision applications such as automated surveillance, video indexing, vehicle navigation, motion based recognition, security and defence areas. Occlusion and noise are generally the biggest problems in any target tracking implementation. Tracking algorithms robustness is a measure of how well it continues to track and when it loses its target. Tracking is the observation of person(s) or object(s) on the move and supplying a timely ordered sequence of respective location data to a model under consideration. It is the process of locating a moving human or object over time using a camera. It is based on computer vision. Image registration is the basic step used in tracking application. It is a process that finds the location where a good matching is obtained by matching the template over the searching area of an input image. Registration algorithm fails in complex situations and loses the target in presence of noise, scaling and transformation changes. To address the above mentioned problems, we use a particle filter based tracking method for efficient tracking. Video shot detection and tracking algorithms have both been extensively researched and have been used in real world applications individually. Very less effort has been made to combine the concepts of video shot detection and tracking which can be of great help in real-world as both the technologies complement each other. Combining the two concepts guarantees a computationally quicker, cost effective solution for tracking on large video database with minimal pre-processing. In this paper Section II covers the concepts of Video shot detection using robust pixel difference method and also demonstrates it effectiveness with results. Section III focuses on concepts of tracking algorithm with results. Section IV elaborates the method of combining the two approaches where tracking algorithm is initiated after every shot change hence serving its final purpose of computationally efficient shot detection cum tracking system.

Video shot detection algorithm based on curvelet transform

The advantage of curvelet transform in processing the "curve singularity" was introduced.Video shot gradual transition detection algorithm based on curvelet transform was presented.The method of calculation and formula was given out.The curvelet transform was used to dissolve image.The high frequency coefficients of curvelet transform acted as the characteristics of the image.The Euclidean distance between characteristics of the sequence images was proposed.The experimental results indicate that the algorithm has better performance than Y.H.HONG's scheme.

Segmentation of news videos based on audio-video information

In this paper, we propose an innovative architecture to segment a news video into the so-called "stories" by both using the included video and audio information. Segmentation of news into stories is one of the key issues for achieving efficient treatment of news-based digital libraries. While the relevance of this research problem is widely recognized in the scientific community, we are in presence of a few established solutions in the field. In our approach, the segmentation is performed in two steps: first, shots are classified by combining three different anchor shot detection algorithms using video information only. Then, the shot classification is improved by using a novel anchor shot detection method based on features extracted from the audio track. Tests on a large database confirm that the proposed system outperforms each single video-based method as well as their combination.

Multimodal Semantic Analysis and Annotation for Basketball Video

This paper presents a new multiple-modality method for extracting semantic information from basketball video. The visual, motion, and audio information are extracted from video to first generate some low-level video segmentation and classification. Domain knowledge is further exploited for detecting interesting events in the basketball video. For video, both visual and motion prediction information are utilized for and scene boundary detection algorithm; this will be followed by scene classification. For audio, audio keysounds are sets of specific audio sounds related to semantic events and a classification method based on hidden Markov model (HMM) is used for audio keysound identification. Subsequently, by analyzing the multimodal information, the positions of potential semantic events, such as foul and shot at the basket, are located with additional domain knowledge. Finally, a video annotation is generated according to MPEG-7 multimedia description schemes (MDSs). Experimental results demonstrate the effectiveness of the proposed method.

인터넷에 기반한 내용기반 검색 시스템 설계

Recently, development of digital technology is occupying a large part of multimedia information like character, voice, image, video, etc. Research about video indexing and retrieval progresses especially in research relative to video. This paper proposes the novel notation in order to retrieve MPEG video in the international standards of moving picture encoding For realizing the retrieval-system, we detect DCT DC coefficient, and then we obtain shot to apply MVC(Mean Value Comparative) notation to image constructed DC coefficient. We choose the key frame for start-frame of a shot, and we have the codebook index generating it using feature of DC image and applying PCA(principal Component Analysis) to the key frame. Also, we realize the retrieval-system through similarity after indexing. We could reduce error detection due to distinguish shot from conventional shot detection algorithm. In the mean time, speed of indexing is faster by PCA due to perform it in the compressed domain, and it has an advantage which is to generate codebook due to use statistical features. Finally, we could realize efficient retrieval-system using MVC and PCA to shot detection and indexing which is important step of retrieval-system, and we using retrieval-system over the internet.

An Accumulation Algorithm for Video Shot Boundary Detection

In this paper, an accumulation algorithm for video shot detection is introduced. The algorithm considers the properties of gradual transition. In a gradual transition, there is only a small difference between consecutive frames. The algorithm remembers the differences between consecutive frames and accumulates them. When the accumulation difference exceeds a threshold, an occurrence of shot transition is declared. Our main contributions are to introduce a frame C that remembers the changes from the beginning of a shot and detect the different types of boundaries (cut, fade, dissolve) at one process. We tested our algorithm with clips extracted from MPEG VCDs. The algorithm showed a good performance in detecting the gradual transitions as well as the abrupt cuts and has the ability to identify different types of boundaries.