The detection of remote sensing (RS) objects plays a crucial role in various earth observation tasks. Current RS object detection methods tend to face great challenges due to large-scale variations of object sizes and limited representation of semantic features, which affect the final bounding box regression results in practice. To address the challenges, we propose a novel Multi-branch and Multi-level Feature Enhancement framework (M2FE-YOLO) to refine feature representation learning for improving the performance of object detection. The proposed M2FE-YOLO primarily comprises three components, i.e., Multi-Branch Feature-awareness based CSP (MBFA-CSP) module, Multi-Level Feature Fusion (MLFF) module, and Shape-IoU as a loss function. MBFA-CSP builds on a dual-scale feature-aware mechanism and a serial convolution pathway to dynamically adjust receptive fields, capturing critical contextual patterns in RS images. MLFF resolves the persistent semantic discrepancy between low-level texture features and high-level abstract representations, enabling precise localization of objects in cluttered RS landscapes. Shape-IoU instead of C-IoU incorporates a geometric compatibility factor (i.e., aspect ratio consistency), and is more crucial for bounding box regression of elongated or irregular RS objects. Compared with existing state-of-the-art methods, extensive experiments on RSOD, NWPU VHR-10, and DOTA datasets quantitatively and qualitatively demonstrate the superiority of the proposed M2FE-YOLO method, achieving up to 92.1%, 93.3%, and 72.2% mAP, respectively. Meanwhile, M2FE-YOLO-OBB achieves an excellent detection result of 73.9% mAP on DOTA dataset for oriented object detection task.

Given a query shoeprint image, shoeprint retrieval aims to retrieve the most similar shoeprints available from a large set of shoeprint images. Most of the existing approaches focus on designing single low-level features to highlight the most similar aspects of shoeprints, but their retrieval precision may vary dramatically with the quality and the content of the images. Therefore, in this paper, we proposed a shoeprint retrieval method to enhance the retrieval precision from two perspectives: (i) integrate the strengths of three kinds of low-level features to yield more satisfactory retrieval results; and (ii) enhance the traditional distance-based similarity by leveraging the information embedded in the neighboring shoeprints. The experiments were conducted on a crime scene shoeprint image dataset, that is, the MUES-SR10KS2S dataset. The proposed method achieved a competitive performance, and the cumulative match score for the proposed method exceeded 92.5% in the top 2% of the dataset, which was composed of 10,096 crime scene shoeprints.

As a kind of forensic evidence, shoeprints have been treated as important as fingerprint and DNA evidence in forensic investigations. Shoeprint verification is used to determine whether two shoeprints could, or could not, have been made by the same shoe. Successful shoeprint verification has tremendous evidentiary value, and the result can link a suspect to a crime, or even link crime scenes to each other. In forensic practice, shoeprint verification is manually performed by forensic experts; however, it is too dependent on experts’ experience. This is a meaningful and challenging problem, and there are few attempts to tackle it in the literatures. In this paper, we propose a multi-layer feature-based method to conduct shoeprint verification automatically. Firstly, we extracted multi-layer features; and then conducted multi-layer feature matching and calculated the total similarity score. Finally, we drew a verification conclusion according to the total similarity score. We conducted extensive experiments to evaluate the effectiveness of the proposed method on two shoeprint datasets. Experimental results showed that the proposed method achieved good performance with an equal error rate (EER) of 3.2% on the MUES-SV1KR2R dataset and an EER of 10.9% on the MUES-SV2HS2S dataset.