Locating people in Real-World for Assisting Crowd Behaviour Analysis Using SSD and Deep SORT Algorithm

Author(s):  
Piyush Juyal ◽  
Sachin Sharma
2018 ◽  
Vol 49 (3) ◽  
pp. 200-216 ◽  
Author(s):  
Hidefumi Nishiyama

The recent proliferation of the securitization of crowded places has led to a growth in the development of technologies of crowd behaviour analysis. However, despite the emerging prominence of crowd surveillance in emergency planning, its impacts on our understanding of security and surveillance have received little discussion. Using the case of crowd surveillance in Tokyo, this article examines the ways in which crowds are simulated, monitored and secured through the technology of crowd behaviour analysis, and discusses the implications on the politics of security. It argues that crowd surveillance constitutes a unique form of the biopolitics of security that targets not the individual body or the social body of population, but the urban body of crowd. The power of normalization in crowd surveillance operates in a preemptive manner through the codification of crowd behaviour that is spatially and temporarily specific. The article also interrogates the introduction of crowd surveillance in relation to racialized logics of suspicion and argues that, despite its appearance as non-discriminatory and ‘a-racial’, crowd surveillance entails the racial coding of crowd behaviour and urban space. The article concludes with the introduction of crowd surveillance as a border control technology, which reorients existing modalities of (in)securitization at airports.


2020 ◽  
Vol 64 ◽  
pp. 318-335 ◽  
Author(s):  
Francisco Luque Sánchez ◽  
Isabelle Hupont ◽  
Siham Tabik ◽  
Francisco Herrera

Author(s):  
D. Bell ◽  
W. Xiao ◽  
P. James

Abstract. A workflow is devised in this paper by which vehicle speeds are estimated semi-automatically via fixed DSLR camera. Deep learning algorithm YOLOv2 was used for vehicle detection, while Simple Online Realtime Tracking (SORT) algorithm enabled for tracking of vehicles. Perspective projection and scale factor were dealt with by remotely mapping corresponding image and real-world coordinates through a homography. The ensuing transformation of camera footage to British National Grid Coordinate System, allowed for the derivation of real-world distances on the planar road surface, and subsequent simultaneous vehicle speed estimations. As monitoring took place in a heavily urbanised environment, where vehicles frequently change speed, estimations were determined consecutively between frames. Speed estimations were validated against a reference dataset containing precise trajectories from a GNSS and IMU equipped vehicle platform. Estimations achieved an average root mean square error and mean absolute percentage error of 0.625 m/s and 20.922 % respectively. The robustness of the method was tested in a real-world context and environmental conditions.


2018 ◽  
Vol 35 (5) ◽  
pp. 753-776 ◽  
Author(s):  
Gaurav Tripathi ◽  
Kuldeep Singh ◽  
Dinesh Kumar Vishwakarma

Sign in / Sign up

Export Citation Format

Share Document