Scipediacontent: Scipediacontent moved page Draft Content 157523056 to Lou et al 2019a

2021-02-02T01:21:36Z

Scipediacontent moved page Draft Content 157523056 to Lou et al 2019a

Scipediacontent: Created page with " == Abstract == Current state-of-the-art single shot object detection pipelines, composed by an object detector such as Yolo, generate multiple detections for each object, re..."

2021-02-02T01:21:32Z

Created page with " == Abstract == Current state-of-the-art single shot object detection pipelines, composed by an object detector such as Yolo, generate multiple detections for each object, re..."

New page

== Abstract ==

Current state-of-the-art single shot object detection pipelines, composed by an object detector such as Yolo, generate multiple detections for each object, requiring a post-processing Non-Maxima Suppression (NMS) algorithm to remove redundant detections. However, this pipeline struggles to achieve high accuracy, particularly in object counting applications, due to a trade-off between precision and recall rates. A higher NMS threshold results in fewer detections suppressed and, consequently, in a higher recall rate, as well as lower precision and accuracy. In this paper, we have explored a new pedestrian detection pipeline which is more flexible, able to adapt to different scenarios and with improved precision and accuracy. A higher NMS threshold is used to retain all true detections and achieve a high recall rate for different scenarios, and a Pedestrian Similarity Extraction (PSE) algorithm is used to remove redundant detentions, consequently improving counting accuracy. The PSE algorithm significantly reduces the detection accuracy volatility and its dependency on NMS thresholds, improving the mean detection accuracy for different input datasets.

== Original document ==

The different versions of the original document can be found in:

* [http://dx.doi.org/10.5220/0007381605480555 http://dx.doi.org/10.5220/0007381605480555]

* [https://doi.org/10.5220/0007381605480555 https://doi.org/10.5220/0007381605480555] under the license cc-by-nc-nd

* [https://dblp.uni-trier.de/db/conf/icpram/icpram2019.html#YangGKLZLW19 https://dblp.uni-trier.de/db/conf/icpram/icpram2019.html#YangGKLZLW19],
: [https://academic.microsoft.com/#/detail/2920941806 https://academic.microsoft.com/#/detail/2920941806]

* [ ]

← Older revision	Revision as of 01:21, 2 February 2021
(No difference)

Lou et al 2019a - Revision history

Scipediacontent: Scipediacontent moved page Draft Content 157523056 to Lou et al 2019a

Scipediacontent: Created page with " == Abstract == Current state-of-the-art single shot object detection pipelines, composed by an object detector such as Yolo, generate multiple detections for each object, re..."