Abstract:
Object detection in remote sensing images (RSIs) is crucial for ground observation applications such as land surveying, urban planning, and precision agriculture. With th...Show MoreMetadata
Abstract:
Object detection in remote sensing images (RSIs) is crucial for ground observation applications such as land surveying, urban planning, and precision agriculture. With the advent of convolutional neural networks, the performance of object detection in RSIs has been significantly improved. However, most studies have focused exclusively on the feature extraction, processing, and representation of geographical objects. The lack of integration of relevant common-sense knowledge has led to some obviously missed detections and illogical false alarms in the detection results. This letter proposes a novel and widely applicable approach for updating and fusing object co-occurrence knowledge into a two-stage multiclass object detection framework, called Auto Learner of Co-occurrence. The method captures the correlation between different object categories during the training process with the Co-occurrence Knowledge Updating module and utilizes the established co-occurrence weight matrix to enhance classification with the Knowledge Fusing module. The effectiveness and adaptability of the proposed method were validated through experiments on two multiclass object detection datasets using four popular two-stage detectors. The experiments also indicate that the speed penalty and the parameter increase resulting from the method are negligible.
Published in: IEEE Geoscience and Remote Sensing Letters ( Volume: 20)