A Weakly-Supervised Deep Network for DSM-Aided Vehicle Detection

Abstract

With the breakthrough of the spatial resolution of optical remote sensing images at the sub-meter level and the explosive development of deep learning, geospatial object detection has achieved a growing interest in remote sensing community. However, labeling large training datasets in object level is still an expensive and tedious procedure. This might lead to the poor model generalization and degraded network learning ability. To this end, a weakly-supervised deep network (WSDN) is developed for geospatial object detection by applying a digital surface model (DSM)-aided auto-labeling and a pre-trained network learned from the task-independent dataset. Experimental results conducted on the stereo aerial imagery of a large camping site are performed to demonstrate that the proposed WSDN yields better detection results, with 62.78% precision and 55.13% recall.

Object Detection and Image Segmentation with Deep Learning on Earth Observation Data: A Review—Part II: Applications

“…In order to create custom datasets, labeling by hand is the most common and accurate but also labor-intensive way, whereas creating datasets from synthetic data is fast, generic and offers an inexpensive alternative as shown by Isikdogan et al [48] and Kong et al [49]. Since synthetic data is hard to create for multispectral and radar remote sensing, weakly supervised approaches [50][51][52] and studies that leverage OSM (Open Street Map) data [53][54][55][56][57][58][59][60][61][62][63][64][65][66][67][68] offer insights in how to use fuzzy data sources [69]. Thus, researchers are encouraged to use such approaches or small-scale hand-labeled datasets for proof-of-concept studies in order to build custom, large-scale, deep-learning datasets in the next step.…”

RSImageNet: A Universal Deep Semantic Segmentation Lifecycle for Remote Sensing Images

“…Although deep learning methods have been successfully applied to the classification of remote sensing images, a large scale of training data should be acquired to train a successful DNN. In real applications, such as disaster monitoring [1] and urban planning [3], it is difficult and expensive to obtain labeled target data to train a proper DNN model to generate classification maps for disaster risk assessment [55], the detection of urban growth [56], and monitoring traffic [57] or assessment of population [58]. To generate classification maps for these applications using deep learning methods, traditionally, ground surveys and situation simulation are adopted to gain more labeled data [55], [59], [60], which requires lots of manual work.…”