透過您的圖書館登入
IP:18.117.196.184
  • 期刊

基於視覺之停車空位偵測技術

Vision-Based Parking Spaces Detection

摘要


在都市區域中,一個日常生活的大問題是停車空位的找尋。因此,本篇論文提出了一個新穎的停車場空位偵測的方法,首先透過使用一個八類的支持向量機(8-class Support Vector Machine)分類器來分析停車場上所拍攝的視訊,推算出停車位為空位以及被車佔據的可能性,同時為了考慮相鄰停車位之間的關聯性,更進一步藉由馬可夫隨機場域(MRF)架構,將支持向量機分類器於不同停車位置上的輸出結果整合在一起。經過這樣的資訊整合過程,使得相鄰停車位之間的遮蔽,以及陰影所導致的偵測效果不佳等現象可以被有效的改善。最後,實驗的結果顯示所提方法可以穩定偵測停車場的空位狀態。

並列摘要


A major problem in metropolitan areas is searching for parking spaces. In this paper, we propose a novel method for parking space detection. Given input video captured by a camera, we can distinguish the empty spaces from the occupied spaces by using an 8-class Support Vector Machine (SVM) classifier with probabilistic outputs. Considering the inter-space correlation, the outputs of the SVM classifier are fused together using a Markov Random Field (MRF) framework. The detection performance is improved, even when there are significant occlusion and shadowing effects in the scene. Experimental results are given to show the robustness of the proposed approach.

延伸閱讀