Matches in SemOpenAlex for { <https://semopenalex.org/work/W3090117981> ?p ?o ?g. }
- W3090117981 abstract "Event cameras encode visual information with high temporal precision, low data-rate, and high-dynamic range. Thanks to these characteristics, event cameras are particularly suited for scenarios with high motion, challenging lighting conditions and requiring low latency. However, due to the novelty of the field, the performance of event-based systems on many vision tasks is still lower compared to conventional frame-based solutions. The main reasons for this performance gap are: the lower spatial resolution of event sensors, compared to frame cameras; the lack of large-scale training datasets; the absence of well established deep learning architectures for event-based processing. In this paper, we address all these problems in the context of an event-based object detection task. First, we publicly release the first high-resolution large-scale dataset for object detection. The dataset contains more than 14 hours recordings of a 1 megapixel event camera, in automotive scenarios, together with 25M bounding boxes of cars, pedestrians, and two-wheelers, labeled at high frequency. Second, we introduce a novel recurrent architecture for event-based detection and a temporal consistency loss for better-behaved training. The ability to compactly represent the sequence of events into the internal memory of the model is essential to achieve high accuracy. Our model outperforms by a large margin feed-forward event-based architectures. Moreover, our method does not require any reconstruction of intensity images from events, showing that training directly from raw events is possible, more efficient, and more accurate than passing through an intermediate intensity image. Experiments on the dataset introduced in this work, for which events and gray level images are available, show performance on par with that of highly tuned and studied frame-based detectors." @default.
- W3090117981 created "2020-10-08" @default.
- W3090117981 creator A5006902285 @default.
- W3090117981 creator A5029899808 @default.
- W3090117981 creator A5032245395 @default.
- W3090117981 creator A5047652078 @default.
- W3090117981 creator A5079598613 @default.
- W3090117981 date "2020-09-28" @default.
- W3090117981 modified "2023-10-01" @default.
- W3090117981 title "Learning to Detect Objects with a 1 Megapixel Event Camera." @default.
- W3090117981 cites W121978728 @default.
- W3090117981 cites W1485009520 @default.
- W3090117981 cites W1522301498 @default.
- W3090117981 cites W1532362218 @default.
- W3090117981 cites W1604973310 @default.
- W3090117981 cites W1606576718 @default.
- W3090117981 cites W1614298861 @default.
- W3090117981 cites W1861492603 @default.
- W3090117981 cites W1901129140 @default.
- W3090117981 cites W1980178290 @default.
- W3090117981 cites W1998339166 @default.
- W3090117981 cites W2004360097 @default.
- W3090117981 cites W2016574277 @default.
- W3090117981 cites W2039573396 @default.
- W3090117981 cites W2076661751 @default.
- W3090117981 cites W2085261163 @default.
- W3090117981 cites W2150355110 @default.
- W3090117981 cites W2194775991 @default.
- W3090117981 cites W2469278928 @default.
- W3090117981 cites W2472115300 @default.
- W3090117981 cites W2513853720 @default.
- W3090117981 cites W2547418827 @default.
- W3090117981 cites W2594491944 @default.
- W3090117981 cites W2767263766 @default.
- W3090117981 cites W2783525259 @default.
- W3090117981 cites W2798878556 @default.
- W3090117981 cites W2805938119 @default.
- W3090117981 cites W2842511635 @default.
- W3090117981 cites W2891530223 @default.
- W3090117981 cites W2894428090 @default.
- W3090117981 cites W2895922401 @default.
- W3090117981 cites W2898457776 @default.
- W3090117981 cites W2899000831 @default.
- W3090117981 cites W2904275768 @default.
- W3090117981 cites W2905199590 @default.
- W3090117981 cites W2922107638 @default.
- W3090117981 cites W2922501539 @default.
- W3090117981 cites W2953106684 @default.
- W3090117981 cites W2955504279 @default.
- W3090117981 cites W2962804204 @default.
- W3090117981 cites W2963037989 @default.
- W3090117981 cites W2963116854 @default.
- W3090117981 cites W2963212638 @default.
- W3090117981 cites W2963351448 @default.
- W3090117981 cites W2963402657 @default.
- W3090117981 cites W2963510238 @default.
- W3090117981 cites W2963952467 @default.
- W3090117981 cites W2964132169 @default.
- W3090117981 cites W2964273528 @default.
- W3090117981 cites W2965867763 @default.
- W3090117981 cites W2971854498 @default.
- W3090117981 cites W2981462813 @default.
- W3090117981 cites W2982632705 @default.
- W3090117981 cites W2993984216 @default.
- W3090117981 cites W2998281665 @default.
- W3090117981 cites W3000845761 @default.
- W3090117981 cites W3010268791 @default.
- W3090117981 cites W3015932348 @default.
- W3090117981 cites W3097883549 @default.
- W3090117981 cites W3102178346 @default.
- W3090117981 cites W3106250896 @default.
- W3090117981 cites W3110053799 @default.
- W3090117981 hasPublicationYear "2020" @default.
- W3090117981 type Work @default.
- W3090117981 sameAs 3090117981 @default.
- W3090117981 citedByCount "2" @default.
- W3090117981 countsByYear W30901179812020 @default.
- W3090117981 countsByYear W30901179812021 @default.
- W3090117981 crossrefType "posted-content" @default.
- W3090117981 hasAuthorship W3090117981A5006902285 @default.
- W3090117981 hasAuthorship W3090117981A5029899808 @default.
- W3090117981 hasAuthorship W3090117981A5032245395 @default.
- W3090117981 hasAuthorship W3090117981A5047652078 @default.
- W3090117981 hasAuthorship W3090117981A5079598613 @default.
- W3090117981 hasConcept C121332964 @default.
- W3090117981 hasConcept C126042441 @default.
- W3090117981 hasConcept C138885662 @default.
- W3090117981 hasConcept C151730666 @default.
- W3090117981 hasConcept C154945302 @default.
- W3090117981 hasConcept C27206212 @default.
- W3090117981 hasConcept C2778738651 @default.
- W3090117981 hasConcept C2778924833 @default.
- W3090117981 hasConcept C2779343474 @default.
- W3090117981 hasConcept C2779662365 @default.
- W3090117981 hasConcept C31972630 @default.
- W3090117981 hasConcept C3261483 @default.
- W3090117981 hasConcept C41008148 @default.
- W3090117981 hasConcept C62520636 @default.
- W3090117981 hasConcept C63584917 @default.
- W3090117981 hasConcept C76155785 @default.