Tree-based vehicle color classification using spatial features on publicly available continuous data

Several recent investigations attempt to classify vehicles into a small number (5-7) of colors. A significant complication arises, however; a large proportion of vehicles (>50%) are various shades of gray: white, black, silver, gray, and variations such as gun metal and pearly white. Distinguishing such shades of gray in vehicle body color from lighting changes is an unsolved problem. Furthermore, previous studies have evaluated their performance on private datasets precluding a comparison of methodologies. In this paper, we release a public dataset with ground truth color classification for future evaluations and comparisons based on the publicly available i-LIDS data [9]. We describe a method to perform vehicle color classification into 7 frequently occurring colors including dark red, dark blue and light silver, using pose dependent vehicle detection, vehicle alignment, and vehicle body part masks. We introduce new features for tree-based vehicle color classification based on the reliability of color information and the relative color of various vehicle parts.