首页|Researchers' Work from Chongqing University of Posts and Telecommunications Focu ses on Artificial Intelligence (Gws: Rotation Object Detection In Aerial Remote Sensing Images Based On Gauss-wasserstein Scattering)
Researchers' Work from Chongqing University of Posts and Telecommunications Focu ses on Artificial Intelligence (Gws: Rotation Object Detection In Aerial Remote Sensing Images Based On Gauss-wasserstein Scattering)
扫码查看
点击上方二维码区域,可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Investigators publish new report on Ar tificial Intelligence. According to news reporting originating from Chongqing, P eople's Republic of China, by NewsRx correspondents, research stated, "The major ity of existing rotating target detectors inherit the horizontal detection parad igm and design the rotational regression loss based on the inductive paradigm. B ut the loss design limitation of the inductive paradigm makes these detectors ha rdly detect effectively tiny targets with high accuracy, particularly for large- aspect-ratio objects." Our news editors obtained a quote from the research from the Chongqing Universit y of Posts and Telecommunications, "Therefore, in view of the fact that horizont al detection is a special scenario of rotating target detection and based on the relationship between rotational and horizontal detection, we shift from an indu ctive to a deductive paradigm of design to develop a new regression loss functio n named Gauss-Wasserstein scattering (GWS). First, the rotating bounding box is transformed into a two-dimensional Gaussian distribution, and then the regressio n losses between Gaussian distributions are calculated as theWasserstein scatter ; By analyzing the gradient of centroid regression, centroid regression is shown to be able to adjust gradients dynamically based on object characteristics, and small targets requiring high accuracy detection rely on this mechanism, and mor e importantly, it is further demonstrated that GWS is scale-invariant while poss essing an explicit regression logic."
ChongqingPeople's Republic of ChinaA siaArtificial IntelligenceRemote SensingChongqing University of Posts and Telecommunications