有別於一般的物件偵測跟語意分割等視覺問題,本論文希望藉由進一步分析不存在的行人出現於道路街景中的機率,來探討利用周邊資訊間接達成場景感知的可能性。我們的方法建立於生成和鑑別的對抗流程上,藉此實現具備找出遺失的視覺資訊的感知能力。為了產生可用於偵測不存在行人的訓練資料,我們使用了最新的圖像修補技術,即使圖片中的指定區域只存在背景,經過學習後的偵測器依然可以預測該區域觀測到行人的機率。我們根據存在機率將額外的行人放入對應圖片中,再透過使用者研究來評估我們的方法,衡量合成的圖片和真實圖片是否已難以區別。實證研究的結果顯示,我們的方法可以領悟到在道路街景中,何處是合理的行人走路或站立位置的概念。
We explore beyond object detection and semantic segmentation, and propose to address the problem of estimating the presence probabilities of nonexistent pedestrians in a street scene. Our method builds upon a combination of generative and discriminative procedures to achieve the perceptual capability of figuring out missing visual information. We adopt state-of-the-art inpainting techniques to generate the training data for nonexistent pedestrian detection. The learned detector can predict the probability of observing a pedestrian at some location in the current image, even if that location exhibits only the background. We evaluate our method by inserting pedestrians into the image according to the presence probabilities and conducting user study to distinguish real and synthetic images. The empirical results show that our method can capture the idea of where the reasonable places are for pedestrians to walk or stand in a street scene.