Beyond mAP: Towards better evaluation of instance segmentation

Jena, Rohit; Zhornyak, Lukas; Doiphode, Nehal; Buch, Vivek; Gee, James C.; Shi, Jianbo

doi:10.48550/arxiv.2207.01614

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Jaccard Index (also known as Intersection over Union) and Dice Coefficient [60] are key measures that evaluate the overlap between the predicted and ground truth masks, with higher values indicating better agreement. Precision quantifies the accuracy of positive predictions, while recall measures the ability to identify all relevant instances of the object [61]. The F1 Score balances precision and recall, offering a single metric that considers both false positives and false negatives.…”

Section: Quantitative Analysismentioning

confidence: 99%

FusionVision: A Comprehensive Approach of 3D Object Reconstruction and Segmentation from RGB-D Cameras Using YOLO and Fast Segment Anything

El Ghazouali,

Mhirit,

Oukhrid

et al. 2024

Sensors

View full text Add to dashboard Cite

In the realm of computer vision, the integration of advanced techniques into the pre-processing of RGB-D camera inputs poses a significant challenge, given the inherent complexities arising from diverse environmental conditions and varying object appearances. Therefore, this paper introduces FusionVision, an exhaustive pipeline adapted for the robust 3D segmentation of objects in RGB-D imagery. Traditional computer vision systems face limitations in simultaneously capturing precise object boundaries and achieving high-precision object detection on depth maps, as they are mainly proposed for RGB cameras. To address this challenge, FusionVision adopts an integrated approach by merging state-of-the-art object detection techniques, with advanced instance segmentation methods. The integration of these components enables a holistic (unified analysis of information obtained from both color RGB and depth D channels) interpretation of RGB-D data, facilitating the extraction of comprehensive and accurate object information in order to improve post-processes such as object 6D pose estimation, Simultanious Localization and Mapping (SLAM) operations, accurate 3D dataset extraction, etc. The proposed FusionVision pipeline employs YOLO for identifying objects within the RGB image domain. Subsequently, FastSAM, an innovative semantic segmentation model, is applied to delineate object boundaries, yielding refined segmentation masks. The synergy between these components and their integration into 3D scene understanding ensures a cohesive fusion of object detection and segmentation, enhancing overall precision in 3D object segmentation.

show abstract

Section: Quantitative Analysismentioning

confidence: 99%