{"title":"缩小犯罪学与计算机视觉之间的差距:遏制枪支暴力的多学科方法","authors":"Tyler E. Houser, Alan McMillan, Beidi Dong","doi":"10.1057/s41284-024-00423-7","DOIUrl":null,"url":null,"abstract":"<p>Gun violence significantly threatens tens of thousands of people annually in the United States. This paper proposes a multidisciplinary approach to address this issue. Specifically, we bridge the gap between criminology and computer vision by exploring the applicability of firearm object detection algorithms to the criminal justice system. By situating firearm object detection algorithms in situational crime prevention, we outline how they could enhance the current use of closed-circuit television (CCTV) systems to mitigate gun violence. We elucidate our approach to training a firearm object detection algorithm and describe why its results are meaningful to scholars beyond the realm of computer vision. Lastly, we discuss limitations associated with object detection algorithms and why they are valuable to criminal justice practices.</p>","PeriodicalId":47023,"journal":{"name":"Security Journal","volume":"49 1","pages":""},"PeriodicalIF":0.2000,"publicationDate":"2024-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Bridging the gap between criminology and computer vision: A multidisciplinary approach to curb gun violence\",\"authors\":\"Tyler E. Houser, Alan McMillan, Beidi Dong\",\"doi\":\"10.1057/s41284-024-00423-7\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>Gun violence significantly threatens tens of thousands of people annually in the United States. This paper proposes a multidisciplinary approach to address this issue. Specifically, we bridge the gap between criminology and computer vision by exploring the applicability of firearm object detection algorithms to the criminal justice system. By situating firearm object detection algorithms in situational crime prevention, we outline how they could enhance the current use of closed-circuit television (CCTV) systems to mitigate gun violence. We elucidate our approach to training a firearm object detection algorithm and describe why its results are meaningful to scholars beyond the realm of computer vision. Lastly, we discuss limitations associated with object detection algorithms and why they are valuable to criminal justice practices.</p>\",\"PeriodicalId\":47023,\"journal\":{\"name\":\"Security Journal\",\"volume\":\"49 1\",\"pages\":\"\"},\"PeriodicalIF\":0.2000,\"publicationDate\":\"2024-04-02\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Security Journal\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1057/s41284-024-00423-7\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"0\",\"JCRName\":\"LANGUAGE & LINGUISTICS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Security Journal","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1057/s41284-024-00423-7","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"0","JCRName":"LANGUAGE & LINGUISTICS","Score":null,"Total":0}
Bridging the gap between criminology and computer vision: A multidisciplinary approach to curb gun violence
Gun violence significantly threatens tens of thousands of people annually in the United States. This paper proposes a multidisciplinary approach to address this issue. Specifically, we bridge the gap between criminology and computer vision by exploring the applicability of firearm object detection algorithms to the criminal justice system. By situating firearm object detection algorithms in situational crime prevention, we outline how they could enhance the current use of closed-circuit television (CCTV) systems to mitigate gun violence. We elucidate our approach to training a firearm object detection algorithm and describe why its results are meaningful to scholars beyond the realm of computer vision. Lastly, we discuss limitations associated with object detection algorithms and why they are valuable to criminal justice practices.
期刊介绍:
The?Security Journal?is a dynamic publication that keeps you informed about the latest developments and techniques in security management. Written in an accessible style it is the world's premier peer-reviewed journal for today's security researcher and professional. The journal is affiliated to ASIS International and has an advisory board which includes representatives from major associations expert practitioners and leading academics.The?Security Journal?publishes papers at the cutting edge in developing ideas and improving practice focusing on the latest research findings on all aspects of security. Regular features include personal opinions and informed comment on key issues in security as well as incisive reviews of books videos and official reports.What are the benefits of subscribing?Learn from evaluations of the latest security measures policies and initiatives; keep up-to-date with new techniques for managing security as well as the latest findings and recommendations of independent research; understand new perspectives and how they inform the theory and practice of security management.What makes the journal distinct?Articles are jargon free and independently refereed; papers are at the cutting edge in developing ideas and improving practice; we have appointed an Advisory Board which includes representatives from leading associations skilled practitioners and the world's leading academics.How does the journal inform?The?Security Journal?publishes innovative papers highlighting the latest research findings on all aspects of security; incisive reviews of books videos and official reports; personal opinions and informed comment on key issues.Topics covered include:fraudevaluations of security measuresshop theftburglaryorganised crimecomputer and information securityrepeat victimisationviolence within the work placeprivate policinginsuranceregulation of the security industryCCTVtaggingaccess controlaviation securityhealth and safetyarmed robberydesigning out crimesecurity staffoffenders' viewsPlease note that the journal does not accept technical or mathematic submissions or research based on formulas or prototypes.