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

By T. Mundhenk, Goran Konjevod, Wesam A. Sakla, Kofi Boakye. European Conference on Computer Vision, 2016

392 citations recorded by the source corpus.

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.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/b462a056fcebd018d41e4fd3a2c94636c3cd01a2

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Tackling Climate Change with Machine Learning (2019, background): “[168] T Nathan Mundhenk, Goran Konjevod, Wesam A Sakla, and Kofi Boakye.”
Drone-Based Object Counting by Spatially Regularized Regional Proposal Network (2017, methodology): “Hence, we follow the setting from [18] and train the network with a different output number to make this regression-based method compatible with the two datasets.”
iSAID: A Large-scale Dataset for Instance Segmentation in Aerial Images (2019, background): “In contrast, aerial images have a very large resolution: for instance the width of some images in COWC [23] dataset is up to 19,000 pixels.”
Geography-Aware Self-Supervised Learning (2020, background): “Most of the studies utilize small-scale datasets specific to a small geographical region [3, 16, 29, 14, 18], a few classes [24] or a highly-specific modality, i.”
Efficient image dataset classification difficulty estimation for predicting deep-learning accuracy (2018, methodology): “Visual deep learning enables applications like 3D shape classification [32], multi-label image classification [6], Flyer classification [39], face detection [7], and automatic car counting [35].”
Object Detection in Optical Remote Sensing Images: A Survey and A New Benchmark (2019, background): “ 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 ”
Improving Object Counting with Heatmap Regulation (2018, methodology): “Considering this fact, where counting is the only task at hand, convolutional networks are employed as a high-dimensional regression network to generate a real-valued or discrete count from the input image directly [24,3,6,5,4,7].”
FAIR1M: A Benchmark Dataset for Fine-grained Object Recognition in High-Resolution Remote Sensing Imagery (2021, background): “The COWC dataset [37] only has one object category.”
Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges (2021, neutral): “[36], vehicle datasets [8], [15], [16], [26], [37], [38], [39], ship datasets [4], [40], and plane datasets [17], [41].”
Learning Multi-Level Density Maps for Crowd Counting (2020, methodology): “In addition, crowd counting can be widely used in other domains such as traffic monitoring [8]–[10], wildlife”
Small-Object Detection in Remote Sensing Images with End-to-End Edge-Enhanced GAN and Object Detector Network (2020, methodology): “Cars overhead with context (COWC) dataset [31] contains 15 cm (one pixel cover 15 cm distance at ground level) satellite images from six different regions.”
SpaceNet: A Remote Sensing Dataset and Challenge Series (2018, background): “Another useful overhead dataset (though not so relevant to foundational mapping) is the COWC dataset [10] of cars, with 15cm aerial imagery collected over six different geographic regions; labels consist of a point at the centroid of each car.”
A Survey of Recent Advances in CNN-based Single Image Crowd Counting and Density Estimation (2017, background): “[69] addressed the problem of automated counting of automobiles from satellite/aerial platforms.”
Vision Meets Drones: A Challenge (2018, background): “2k 9 733 1024× 1024 2015 COWC [19] aerial 32.”