| 1. |
- Ahrnbom, Martin, et al.
(författare)
-
Improving a real-time object detector with compact temporal information
- 2018
-
Ingår i: International Conference on Computer Vision Workshops, 2017 : Computer Vision for Road Scene Understanding and Autonomous Driving Workshop - Computer Vision for Road Scene Understanding and Autonomous Driving Workshop. ; , s. 190-197
-
Konferensbidrag (refereegranskat)abstract
- Neural networks designed for real-time object detectionhave recently improved significantly, but in practice, look-ing at only a single RGB image at the time may not be ideal.For example, when detecting objects in videos, a foregrounddetection algorithm can be used to obtain compact temporaldata, which can be fed into a neural network alongside RGBimages. We propose an approach for doing this, based onan existing object detector, that re-uses pretrained weightsfor the processing of RGB images. The neural network wastested on the VIRAT dataset with annotations for object de-tection, a problem this approach is well suited for. The ac-curacy was found to improve significantly (up to 66%), witha roughly 40% increase in computational time.
|
|
| 2. |
|
|
| 3. |
- Madsen, Tanja, et al.
(författare)
-
Mobile Application for Naturalistic Walking/Cycling Data Collection
- 2017
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- Two smartphone applications were developed with the aim of harvesting insights of vulnerable road user accidents. The apps require a backend database with software tools for generating and managing questionnaires, etc. Such a system was developed using a MySQL database where a user-friendly platform has been developed in CakePHP. The backend system has been successfully developed and been used to handle more than 11,000 participants. The original idea was to monitor VRU via apps to detect when they may have been involved in an accident as pedestrian or cyclist based on the motion patterns from the smartphone’s motion sensors (accelerometer, gyroscope) and collect as much information as possible regarding the accident automatically (e.g. time and location of the accident). If an accident was detected, the road user should receive a questionnaire to provide detailed information of the accident (e.g. road surface conditions, lighting conditions, other road users involved). This app was used by more than 400 participants resulting in a large amount of data.
|
|
