| 1. |
- Chen, Guang, et al.
(författare)
-
NeuroIV : Neuromorphic Vision Meets Intelligent Vehicle Towards Safe Driving With a New Database and Baseline Evaluations
- 2022
-
Ingår i: IEEE transactions on intelligent transportation systems (Print). - : Institute of Electrical and Electronics Engineers (IEEE). - 1524-9050 .- 1558-0016. ; 23:2, s. 1171-1183
-
Tidskriftsartikel (refereegranskat)abstract
- Neuromorphic vision sensors such as the Dynamic and Active-pixel Vision Sensor (DAVIS) using silicon retina are inspired by biological vision, they generate streams of asynchronous events to indicate local log-intensity brightness changes. Their properties of high temporal resolution, low-bandwidth, lightweight computation, and low-latency make them a good fit for many applications of motion perception in the intelligent vehicle. However, as a younger and smaller research field compared to classical computer vision, neuromorphic vision is rarely connected with the intelligent vehicle. For this purpose, we present three novel datasets recorded with DAVIS sensors and depth sensor for the distracted driving research and focus on driver drowsiness detection, driver gaze-zone recognition, and driver hand-gesture recognition. To facilitate the comparison with classical computer vision, we record the RGB, depth and infrared data with a depth sensor simultaneously. The total volume of this dataset has 27360 samples. To unlock the potential of neuromorphic vision on the intelligent vehicle, we utilize three popular event-encoding methods to convert asynchronous event slices to event-frames and adapt state-of-the-art convolutional architectures to extensively evaluate their performances on this dataset. Together with qualitative and quantitative results, this work provides a new database and baseline evaluations named NeuroIV in cross-cutting areas of neuromorphic vision and intelligent vehicle.
|
|
| 2. |
- Xiong, Zhifang, et al.
(författare)
-
Intensified aridity over the Indo-Pacific Warm Pool controlled by ice-sheet expansion during the Last Glacial Maximum
- 2022
-
Ingår i: Global and Planetary Change. - : Elsevier BV. - 0921-8181. ; 217
-
Tidskriftsartikel (refereegranskat)abstract
- The magnitude, direction and cause of precipitation changes across the Indo-Pacific Warm Pool (IPWP) during the Last Glacial Maximum (LGM) remain elusive. In particular, it is still inconclusive whether tropical or extra-tropical factors controlled such precipitation changes. Determining the spatio-temporal distribution of precipitation in the IPWP during the LGM is a valid strategy to address this issue, but the existing precipitation records are dominantly from maritime continents and marginal seas, with few data from pelagic oceans. In order to fill this gap, we analyzed the oxygen isotopic compositions of single Ethmodiscus rex diatom frustules (δ18OE. rex) from a sediment core (WPD-03) consisting of laminated diatom mats (LDMs) in the eastern Philippine Sea (EPS). δ18OE. rex was controlled mainly by sea-surface salinity variation and, thus, can reflect open-ocean precipitation changes across the IPWP. Our precipitation proxy records, in combination with existing published data, reveal spatial patterns of precipitation change that indicate overall drying across the IPWP during the LGM. Based on a comparison of paleoclimatic records with modeling results, we propose that extra-tropical factors (ice-sheet size) controlled precipitation variability in the IPWP during the LGM through a combination of zonal shifts of ENSO and meridional migration of the ITCZ. Strong aridity during the LGM prevented formation of a subsurface barrier layer and, hence, allowed accessing of sufficient nutrients to surface waters, stimulating blooms of E. rex and subsequent formation of LDMs in the IPWP. These findings suggest an important role for high-latitude climate in the tropical hydrological cycle during the LGM.
|
|
