A Large Contextual Dataset for Classification, Detection and Counting of Cars with Deep Learning

Abstract

Abstract. We have created a large diverse set of cars from overhead images 1 , which are useful for training a deep learner to binary classify, detect and count them. The dataset and all related material will be made publically available. The set contains contextual matter to aid in identification of difficult targets. We demonstrate classification and detection on this dataset using a neural network we call ResCeption. This network combines residual learning with Inception-style layers and is used to count cars in one look. This is a new way to count objects rather than by localization or density estimation. It is fairly accurate, fast and easy to implement. Additionally, the counting method is not car or scene specific. It would be easy to train this method to count other kinds of objects and counting over new scenes requires no extra set up or assumptions about object locations.

Object detection in optical remote sensing images: A survey and a new benchmark

“…Therefore, it is not surprising that the object detectors learned from natural scene images are not easily transferable to remote sensing images. Although several popular object detection datasets, such as NWPU VHR-10 (Cheng et al, 2016a), UCAS-AOD (Zhu et al, 2015a), COWC (Mundhenk et al, 2016), and DOTA (Xia et al, 2018), are proposed in the earth observation community, they are still far from satisfying the requirements of deep learning algorithms. To date, significant efforts (Cheng and Han, 2016;Cheng et al, 2016a;Das et al, 2011;Han et al, 2015;Li et al, 2018;Razakarivony and Jurie, 2015;Tang et al, 2017b;Xia et al, 2018;Yokoya and Iwasaki, 2015;Zhang et al, 2016;Zhu et al, 2017) have been made for object detection in remote sensing images.…”

A CNN-Based Method of Vehicle Detection from Aerial Images Using Hard Example Mining

“…We employed the simple sliding window method and CNN architecture, because we mainly focused on the effectiveness of our HEM method. Our HEM method is easily scaled, for instance, by replacing the CNN architecture with a richer one, such as the model used in [18].…”

“…For instance, [16] reported an F1 of 0.83, and [18] reported very high F1 of 0.94. Although it is not a fair comparison, because the training data and test settings are totally different, 0.71 is not the best.…”

“…The primary reason would be the insufficiency of our training data. The authors in [16] used the Munich dataset [29], which has 9433 annotated vehicles, and [18] proposed and used the COWC dataset, which has 32,716 annotated vehicles. Compared to those datasets, our training data were sparse.…”

“…Another reason would be the simplicity of our CNN architecture. When we compared just the numbers of convolutional layers in each method, [16] had five and [18] had 50, whereas our model only had three.…”