TY - GEN
T1 - Asynchronous Events-based Panoptic Segmentation using Graph Mixer Neural Network
AU - Kachole, Sanket
AU - Alkendi, Yusra
AU - Baghaei Naeini, Fariborz
AU - Makris, Dimitrios
AU - Zweiri, Yahya
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - In the context of robotic grasping, object segmentation encounters several difficulties when faced with dynamic conditions such as real-time operation, occlusion, low lighting, motion blur, and object size variability. In response to these challenges, we propose the Graph Mixer Neural Network that includes a novel collaborative contextual mixing layer, applied to 3D event graphs formed on asynchronous events. The proposed layer is designed to spread spatiotemporal correlation within an event graph at four nearest neighbor levels parallelly. We evaluate the effectiveness of our proposed method on the Event-based Segmentation (ESD) Dataset, which includes five unique image degradation challenges, including occlusion, blur, brightness, trajectory, scale variance, and segmentation of known and unknown objects. The results show that our proposed approach outperforms state-of-the-art methods in terms of mean intersection over the union and pixel accuracy. Code available at: https://github.com/sanket0707/GNN-Mixer.git
AB - In the context of robotic grasping, object segmentation encounters several difficulties when faced with dynamic conditions such as real-time operation, occlusion, low lighting, motion blur, and object size variability. In response to these challenges, we propose the Graph Mixer Neural Network that includes a novel collaborative contextual mixing layer, applied to 3D event graphs formed on asynchronous events. The proposed layer is designed to spread spatiotemporal correlation within an event graph at four nearest neighbor levels parallelly. We evaluate the effectiveness of our proposed method on the Event-based Segmentation (ESD) Dataset, which includes five unique image degradation challenges, including occlusion, blur, brightness, trajectory, scale variance, and segmentation of known and unknown objects. The results show that our proposed approach outperforms state-of-the-art methods in terms of mean intersection over the union and pixel accuracy. Code available at: https://github.com/sanket0707/GNN-Mixer.git
UR - https://www.scopus.com/pages/publications/85170820348
U2 - 10.1109/CVPRW59228.2023.00429
DO - 10.1109/CVPRW59228.2023.00429
M3 - Conference contribution
AN - SCOPUS:85170820348
T3 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
SP - 4083
EP - 4092
BT - Proceedings - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023
PB - IEEE Computer Society
T2 - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023
Y2 - 18 June 2023 through 22 June 2023
ER -