Tactical reconnaissance using small unmanned aerial vehicles has become a common military scenario. However, since their sensor systems are usually limited to rudimentary visual or thermal imaging, the detection of camouflaged objects can be a particularly hard challenge. With respect to SWaP-C criteria, multispectral sensors represent a promising solution to increase the spectral information that could lead to unveiling camouflage. Therefore, this paper investigates and evaluates the applicability of four well-known hyperspectral anomaly detection methods (RX, LRX, CRD, and AED) and a method developed by the authors called local point density (LPD) for near real-time camouflage detection in multispectral imagery based on a specially created dataset. Results show that all targets in the dataset could successfully be detected with an AUC greater than 0.9 by multiple methods, with some methods even reaching an AUC relatively close to 1.0 for certain targets. Yet, great variations in detection performance over all targets and methods were observed. The dataset was additionally enhanced by multiple vegetation indices (BNDVI, GNDVI, and NDRE), which resulted in generally higher detection performances of all methods. Overall, the results demonstrated the general applicability of the hyperspectral anomaly detection methods for camouflage detection in multispectral imagery.
To improve the management of multispectral sensor systems on small reconnaissance drones, this paper proposes an approach to predict the performance of a sensor band with respect to its ability to expose camouflaged targets under a given environmental context. As a reference for sensor performance, a new metric is introduced that quantifies the visibility of camouflaged targets in a particular sensor band: the Target Visibility Index (TVI). For the sensor performance prediction, several machine learning models are trained to learn the relationship between the TVI for a specific sensor band and an environmental context state extracted from the visual band by multiple image descriptors. Using a predicted measure of performance, the sensor bands are ranked according to their significance. For the training and evaluation of the performance prediction approach, a dataset featuring 853 multispectral captures and numerous camouflaged targets in different environments was created and has been made publicly available for download. The results show that the proposed approach can successfully determine the most informative sensor bands in most cases. Therefore, this performance prediction approach has great potential to improve camouflage detection performance in real-world reconnaissance scenarios by increasing the utility of each sensor band and reducing the associated workload of complex multispectral sensor systems.
Multispectral sensors provide valuable spectral information suitable for a variety of remote sensing applications, especially when cost-effectiveness, portability, and energy efficiency are essential, such as on small tactical drones. Since all materials have unique spectral signatures, this spectral information can be utilized to detect camouflaged targets in military reconnaissance scenarios. However, varying environmental conditions like vegetation and weather in real-world reconnaissance scenarios, and the computational complexity introduced by the large number of bands, make successful camouflage detections difficult. To address these issues, a novel sensor-managed anomaly detection method is proposed. This approach determines a subset of sensor bands of a multispectral imaging system based on current environmental conditions and their ability to expose camouflaged targets. Instead of processing all available bands, a spectral anomaly detector then processes only this subset of bands. To evaluate the robustness of the proposed approach, four different spectral anomaly detection methods are employed and compared: the RX detector, LRX detector, AED detector, and LPD detector. Experiments on an extensive multi-spectral dataset for camouflage detection show nearly equivalent detection performance when spectral anomaly detectors are applied to the managed subset compared to all sensor bands. This demonstrates the effectiveness of the proposed approach in reducing computational complexity while maintaining detection performance, which is particularly important for small tactical drones in military reconnaissance scenarios.