Multitarget Multiple-Instance Learning for Hyperspectral Target Detection

Meerdink, Susan; Bocinsky, James; Zare, Alina; Kroeger, Nicholas; McCurley, Connor H.; Shats, Daniel; Gader, Paul D.

doi:10.1109/tgrs.2021.3060966

Cited by 12 publications

(2 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hyperspectral imagery is collected in very narrow spectral sampling intervals [13][14][15]. The availability of a high number of spectral bands in hyperspectral data considerably facilitates the detection of targets with similar spectral responses [16][17][18]. However, one of the limitations of the hyperspectral dataset is the low temporal resolution, which can be efficiently resolved using the recent and future series of hyperspectral sensors (e.g., Hyperspectral Infrared Imager (HyspIRI), PRISMA (PRecursore IperSpettrale Della Missione Applicativa), and HypXIM).…”

Section: Introductionmentioning

confidence: 99%

A Multi-Dimensional Deep Siamese Network for Land Cover Change Detection in Bi-Temporal Hyperspectral Imagery

Seydi

Shah-Hosseini

Amani³

2022

Sustainability

View full text Add to dashboard Cite

In this study, an automatic Change Detection (CD) framework based on a multi-dimensional deep Siamese network was proposed for CD in bi-temporal hyperspectral imagery. The proposed method has two main steps: (1) automatic generation of training samples using the Otsu algorithm and the Dynamic Time Wrapping (DTW) predictor, and (2) binary CD using a multidimensional multi-dimensional Convolution Neural Network (CNN). Two bi-temporal hyperspectral datasets of the Hyperion sensor with a variety of land cover classes were used to evaluate the performance of the proposed method. The results were also compared to reference data and two state-of-the-art hyperspectral change detection (HCD) algorithms. It was observed that the proposed method relatively had higher accuracy and lower False Alarm (FA) rate, where the average Overall Accuracy (OA) and Kappa Coefficient (KC) were more than 96% and 0.90, respectively, and the average FA rate was lower than 5%.

show abstract

Section: Introductionmentioning

confidence: 99%

A Multi-Dimensional Deep Siamese Network for Land Cover Change Detection in Bi-Temporal Hyperspectral Imagery

Seydi

Shah-Hosseini

Amani³

2022

Sustainability

View full text Add to dashboard Cite

show abstract

“…Recently, the deep neural network simulating human brain intelligence has made revolutionary progress in the field of visual tasks [1][2][3] and can realize 2D object detection, recognition and tracking [4] [5]. The traditional 2D object detection methods based on deep-learning mainly regress object position via anchor mechanism, such as SSD [6], YOLOX [7], RetinaNet [8], Mask RCNN [9], YOLOF [10], etc.…”

Section: Introductionmentioning

confidence: 99%

Improved Attention Mechanism-Based Object Detection Method

Zhou

Chen

2022

Frontiers in Artificial Intelligence and Applications

View full text Add to dashboard Cite

Aiming at the problems of low detection accuracy for objects with non-significant features in the FCOS network, a new object detection method based on attention mechanism is proposed to improve the performance of FCOS network, which can effectively guide the network to focus on the detailed features. According to the verification experimental results on KITTI dataset, the AP value of the improved attention mechanism-based method for car and person detection is improved by 1.1% and 4.9% compared with the standard FCOS network, respectively, and the average category accuracy value is improved by 3%. Thus, the experimental results show the effectiveness of the proposed method.

show abstract