English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

Most visual scene understanding tasks in the field of computer vision involveidentification of the objects present in the scene. Image regions likehideouts, turns, & other obscured regions of the scene also contain crucialinformation, for specific surveillance tasks. Task proposed in this paperinvolves the design of an intelligent visual aid for identification of suchlocations in an image, which has either the potential to create an imminentthreat from an adversary or appear as the target zones needing furtherinvestigation. Covert places (CGL) for hiding behind an occluding object areconcealed 3D locations, not detectable from the viewpoint (camera). Hence thisinvolves delineating specific image regions around the projections of outerboundary of the occluding objects, as places to be accessed around thepotential hideouts. CGL detection finds applications in militarycounter-insurgency operations, surveillance with path planning for anexploratory robot. Given an RGB image, the goal is to identify all CGLs in the2D scene. Identification of such regions would require knowledge about the 3Dboundaries of obscuring items (pillars, furniture), their spatial location withrespect to the neighboring regions of the scene. We propose this as a noveltask, termed Covert Geo-Location (CGL) Detection. Classification of any regionof an image as a CGL (as boundary sub-segments of an occluding object thatconceals the hideout) requires examining the 3D relation between boundaries ofoccluding objects and their neighborhoods & surroundings. Our methodsuccessfully extracts relevant depth features from a single RGB image andquantitatively yields significant improvement over existing object detectionand segmentation models adapted and trained for CGL detection. We alsointroduce a novel hand-annotated CGL detection dataset containing 1.5Kreal-world images for experimentation.

Catch Me if You Can: A Novel Task for Detection of Covert Geo-Locations (CGL)