A Large Contextual Dataset for Classification, Detection and Counting of Cars with Deep Learning
This work addresses the need for efficient object counting in computer vision, particularly for applications like traffic monitoring, but it appears incremental as it builds on existing deep learning techniques.
The authors tackled the problem of car counting from overhead images by creating a large contextual dataset and developing ResCeption, a neural network that counts cars in one look without localization or density estimation. The method is described as fairly accurate, fast, easy to implement, and generalizable to other objects and scenes.
We have created a large diverse set of cars from overhead images, 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.