Behavior perception with fine granularity can offer much more valuable information, e.g. which and why products people are often interested in will not be purchased in shopping. In this paper, we propose a RFID-based method to perceive slight motion of a target product with RFID tag for mining customer's behaviors. However, the interference from human movements in the reading zone is a challenge to result in false positives. To address this problem, we first compute virtual displacements of the target RFID tag and then adopt Support Vector Machines to recognize absence or presence of human motion near the tag. Next, we divide the surveillance region into mm-level grids to construct similarity matrixes of the tracked tag before and after human motion, which can accurately distinguish absence or presence of tag motion. Indeed, the optimization method based on phase-ambiguity is introduced to reduce computations. The results show that our method can achieve the average scenario classification accuracy of 96.3 % and the average slight tag motion perception accuracy of 100 % with the hypersensitivity of 1 mm.