Fast Training Data Acquisition for Object Detection and Segmentation using Black Screen Luminance Keying
This provides a fast and straightforward method for small-scale applications to adopt deep learning by reducing data acquisition time and cost, though it is incremental as it builds on chroma keying concepts.
The paper tackles the problem of acquiring annotated training data for object detection and segmentation by proposing luminance keying with a black screen to automatically mask objects and place them on random backgrounds, achieving favorable performance on the YCB-V object set compared to conventional techniques like rendering, without needing 3D models and in a fraction of the time.
Deep Neural Networks (DNNs) require large amounts of annotated training data for a good performance. Often this data is generated using manual labeling (error-prone and time-consuming) or rendering (requiring geometry and material information). Both approaches make it difficult or uneconomic to apply them to many small-scale applications. A fast and straightforward approach of acquiring the necessary training data would allow the adoption of deep learning to even the smallest of applications. Chroma keying is the process of replacing a color (usually blue or green) with another background. Instead of chroma keying, we propose luminance keying for fast and straightforward training image acquisition. We deploy a black screen with high light absorption (99.99\%) to record roughly 1-minute long videos of our target objects, circumventing typical problems of chroma keying, such as color bleeding or color overlap between background color and object color. Next we automatically mask our objects using simple brightness thresholding, saving the need for manual annotation. Finally, we automatically place the objects on random backgrounds and train a 2D object detector. We do extensive evaluation of the performance on the widely-used YCB-V object set and compare favourably to other conventional techniques such as rendering, without needing 3D meshes, materials or any other information of our target objects and in a fraction of the time needed for other approaches. Our work demonstrates highly accurate training data acquisition allowing to start training state-of-the-art networks within minutes.