Learning Two-View Correspondences and Geometry via Local Neighborhood Correlation

Seeking quality feature correspondences (also known as matches) is a foundational step in computer vision. In our work, a novel and effective network with a stable local constraint, named the Local Neighborhood Correlation Network (LNCNet), is proposed to capture abundant contextual information of each correspondence in the local region, followed by calculating the essential matrix and camera pose estimation. Firstly, the k-Nearest Neighbor (KNN) algorithm is used to divide the local neighborhood roughly. Then, we calculate the local neighborhood correlation matrix (LNC) between the selected correspondence and other correspondences in the local region, which is used to filter outliers to obtain more accurate local neighborhood information. We cluster the filtered information into feature vectors containing richer neighborhood contextual information so that they can be used to more accurately determine the probability of correspondences as inliers. Extensive experiments have demonstrated that our proposed LNCNet performs better than some state-of-the-art networks to accomplish outlier rejection and camera pose estimation tasks in complex outdoor and indoor scenes.

The Research on Forest Resources Change Detection Based on C5.0 Algorithm and Neighborhood Correlation Image Analysis

With double-temporal Landsat TM and ETM+ datasets, the change information of forest resources of Culai Mountain in Shandong Province was explored. This paper applies decision tree classification based on C5.0 algorithm and neighborhood correlation image analysis to detect forest change information，and compares the three different detection methods：1)C5.0 classifies single-temporal data respectively，and extract change information after comparing classification results；2) create C5.0 train rules through double-temporal raw data，then generate change detection map；3)In addition to double-temporal remote sensing data，neighborhood correlation analysis images are also added as one of the data sources of C5.0，and generate change detection map. The experimental result shows that decision tree classification based on C5.0 algorithm can detect change information effectively，and after adding neighborhood correlation analysis images the classification accuracy of change detection was improved.