[vc_empty_space][vc_empty_space]
Camera Latency Review and Parameters Testing for Real-Time Object Detection Implementation
Tanadi R.a, Husni E.a, Emir A.R.a
a Institut Teknologi Bandung, School of Electrical Engineering and Informatics, Bandung, Indonesia
[vc_row][vc_column][vc_row_inner][vc_column_inner][vc_separator css=”.vc_custom_1624529070653{padding-top: 30px !important;padding-bottom: 30px !important;}”][/vc_column_inner][/vc_row_inner][vc_row_inner layout=”boxed”][vc_column_inner width=”3/4″ css=”.vc_custom_1624695412187{border-right-width: 1px !important;border-right-color: #dddddd !important;border-right-style: solid !important;border-radius: 1px !important;}”][vc_empty_space][megatron_heading title=”Abstract” size=”size-sm” text_align=”text-left”][vc_column_text]© 2020 IEEE.In recent years, as computer vision and machine learning technologies continues to improve and become more available to general public, implementation of machine learning and computer vision based object detection also grown in popularity. Even more recently, advancement in computational power had enabled such systems to be implemented to process real time data and output real time decisions, such as surveillance, driving assistance, or pedestrian tracking. Computer vision-based object detection, in general, allows these implementations to be implemented on various kinds of cameras-USB Webcam, IP Camera, etc. While such implementations could do real-time processing and real-time decision making, but computer vision includes capturing process, which sometimes is caused by cameras itself. This paper reviews latencies caused by IP Camera and USB Webcam, by comparing captured stopwatch to real value of the stopwatch, and the data is used to compare those latencies to theoretical standard of real-time, imperceptible latency, to further compiled into a optimized parameters to be used in other implementations. Finally, this paper is used to test whether those latencies could be reduced by optimizing capture parameters so that computer vision implementations are true real-time from capture to output. These optimized settings could yield 176,67 milliseconds latency on USB Camera and 128,4 milliseconds on specific IP Camera.[/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”Author keywords” size=”size-sm” text_align=”text-left”][vc_column_text]Computational power,Driving assistance,Machine learning technology,Optimized parameter,Pedestrian tracking,Real time decision-making,Real time decisions,Realtime processing[/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”Indexed keywords” size=”size-sm” text_align=”text-left”][vc_column_text]frame rate,ip camera,latency,parameters,resolution,usb webcam[/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”Funding details” size=”size-sm” text_align=”text-left”][vc_column_text][/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”DOI” size=”size-sm” text_align=”text-left”][vc_column_text]https://doi.org/10.1109/ICIDM51048.2020.9339646[/vc_column_text][/vc_column_inner][vc_column_inner width=”1/4″][vc_column_text]Widget Plumx[/vc_column_text][/vc_column_inner][/vc_row_inner][/vc_column][/vc_row][vc_row][vc_column][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][/vc_column][/vc_row]