Sökning: WFRF:(Cao Guang) >
Multi-Cue Event Inf...
Multi-Cue Event Information Fusion for Pedestrian Detection With Neuromorphic Vision Sensors
-
- Chen, Guang (författare)
- Tongji Univ, Coll Automot Engn, Shanghai, Peoples R China.;Tech Univ Munich, Robot Artificial Intelligence & Real Time Syst, Munich, Germany.
-
- Cao, Hu (författare)
- Hunan Univ, State Key Lab Adv Design & Mfg Vehicle Body, Changsha, Hunan, Peoples R China.
-
- Ye, Canbo (författare)
- Tongji Univ, Coll Automot Engn, Shanghai, Peoples R China.
-
visa fler...
-
- Zhang, Zhenyan (författare)
- Tongji Univ, Coll Automot Engn, Shanghai, Peoples R China.
-
- Liu, Xingbo (författare)
- Tongji Univ, Coll Automot Engn, Shanghai, Peoples R China.
-
- Mo, Xuhui (författare)
- Hunan Univ, State Key Lab Adv Design & Mfg Vehicle Body, Changsha, Hunan, Peoples R China.
-
- Qu, Zhongnan (författare)
- Swiss Fed Inst Technol, Comp Engn & Networks Lab, Zurich, Switzerland.
-
- Conradt, Jörg (författare)
- KTH,Beräkningsvetenskap och beräkningsteknik (CST)
-
- Roehrbein, Florian (författare)
- Tech Univ Munich, Robot Artificial Intelligence & Real Time Syst, Munich, Germany.
-
- Knoll, Alois (författare)
- Tech Univ Munich, Robot Artificial Intelligence & Real Time Syst, Munich, Germany.
-
visa färre...
-
Tongji Univ, Coll Automot Engn, Shanghai, Peoples R China;Tech Univ Munich, Robot Artificial Intelligence & Real Time Syst, Munich, Germany. Hunan Univ, State Key Lab Adv Design & Mfg Vehicle Body, Changsha, Hunan, Peoples R China. (creator_code:org_t)
- 2019-04-02
- 2019
- Engelska.
-
Ingår i: Frontiers in Neurorobotics. - : FRONTIERS MEDIA SA. - 1662-5218. ; 13
- Relaterad länk:
-
https://doi.org/10.3...
-
visa fler...
-
https://www.frontier...
-
https://urn.kb.se/re...
-
https://doi.org/10.3...
-
visa färre...
Abstract
Ämnesord
Stäng
- Neuromorphic vision sensors are bio-inspired cameras that naturally capture the dynamics of a scene with ultra-low latency, filtering out redundant information with low power consumption. Few works are addressing the object detection with this sensor. In this work, we propose to develop pedestrian detectors that unlock the potential of the event data by leveraging multi-cue information and different fusion strategies. To make the best out of the event data, we introduce three different event-stream encoding methods based on Frequency, Surface of Active Event (SAE) and Leaky Integrate-and-Fire (LIF). We further integrate them into the state-of-the-art neural network architectures with two fusion approaches: the channel-level fusion of the raw feature space and decision-level fusion with the probability assignments. We present a qualitative and quantitative explanation why different encoding methods are chosen to evaluate the pedestrian detection and which method performs the best. We demonstrate the advantages of the decision-level fusion via leveraging multi-cue event information and show that our approach performs well on a self-annotated event-based pedestrian dataset with 8,736 event frames. This work paves the way of more fascinating perception applications with neuromorphic vision sensors.
Ämnesord
- TEKNIK OCH TEKNOLOGIER -- Elektroteknik och elektronik -- Robotteknik och automation (hsv//swe)
- ENGINEERING AND TECHNOLOGY -- Electrical Engineering, Electronic Engineering, Information Engineering -- Robotics (hsv//eng)
Nyckelord
- neuromorphic vision sensor
- event-stream encoding
- object detection
- convolutional neural network
- multi-Cue event information fusion
Publikations- och innehållstyp
- ref (ämneskategori)
- art (ämneskategori)
Hitta via bibliotek
Till lärosätets databas
- Av författaren/redakt...
-
Chen, Guang
-
Cao, Hu
-
Ye, Canbo
-
Zhang, Zhenyan
-
Liu, Xingbo
-
Mo, Xuhui
-
visa fler...
-
Qu, Zhongnan
-
Conradt, Jörg
-
Roehrbein, Flori ...
-
Knoll, Alois
-
visa färre...
- Om ämnet
-
- TEKNIK OCH TEKNOLOGIER
-
TEKNIK OCH TEKNO ...
-
och Elektroteknik oc ...
-
och Robotteknik och ...
- Artiklar i publikationen
-
Frontiers in Neu ...
- Av lärosätet
-
Kungliga Tekniska Högskolan