The Automated Change Detection and Classification Real-time (ACDC-RT) System

Abstract

Abstract-This paper presents an Automated Change Detectionand Classification (ACDC) System, developed by the Naval Research Laboratory (NRL) and the Naval Oceanographic Office (NAVOCEANO), which aids analysts in performing change detection in real-time (RT) by co-registering new and historical imagery and using automated change detection algorithms that suggest imagery changes. In this paper, ACDC-RT components are described and results given from a recent change detection experiment. The Navy requires a real-time change detection and classification system. This paper presents the Automated Change Detection and Classification -Real-Time System (ACDC-RT) developed by the Naval Research Laboratory (NRL) and Naval Oceanographic Office (NAVOCEANO) to assist change detection analysts by co-registering new imagery with historical, over the same area, and using automated algorithms to suggest possible changes between the two imagery sets (i.e., new contacts on the seafloor). ACDC-RT integrates Computer-Aided Detection, Classification, Search, and Feature-matching functions previously developed by NRL. Figure 1 shows the two main ACDC-RT displays: a timebased waterfall display of SSI as it is being collected (top) and a geo-registered waterfall display of historical SSI over the same area (bottom). ACDC-RT algorithms detected a minelike contact in the RT SSI (inset box on top) and matched it with the same contact observed in the past (inset box on the bottom). Public reporting burden for the collection of information is estimated to average 1 hour per response, including the time for reviewing instructions, searching existing data sources, gathering and maintaining the data needed, and completing and reviewing the collection of information. Send comments regarding this burden estimate or any other aspect of this collection of information, including suggestions for reducing this burden, to Washington Headquarters Services, Directorate for Information Operations and Reports, 1215 Jefferson Davis Highway, Suite 1204, Arlington VA 22202-4302. Respondents should be aware that notwithstanding any other provision of law, no person shall be subject to a penalty for failing to comply with a collection of information if it does not display a currently valid OMB control number. Index Terms-Acoustic

Challenges of Automated Change Detection in Repeat-Pass Sas Imagery

“…PROCESSING APPROACHES Early sonar ACD works focused on decision level (contact based) methods for mine hunting, i.e. locating new mine-like contacts without a reference contact in corresponding position [6][7] .…”

Automated change detection using Synthetic Aperture Sonar imagery

“…This paper presents efforts to perform automated change detection between historical SSI (collected during the presurvey) and the new SAS imagery (collected during the Corpus Christi LOE) using the authors' Automated Change Detection and Classification (ACDC) system. ACDC currently automates the change detection process with sophisticated algorithms operating on high-resolution SSI [4][5][6][7][8][9]. The authors first discuss briefly how their Automated Target Recognition (ATR) component of ACDC currently works with SSI.…”

An automated change detection approach for mine recognition using sidescan sonar data

“…Thus, compared to a few target pixels, a large number of pixels in the sonar images are made up of environment noise and target-like objects that are difficult to discriminate. Meanwhile, the stationary objects on the seafloor tend to have position error when compared among bi-temporal sonar images taken in t 1 and t 2 , due to the error generated in the data collection process [6]. The other issue is the challenge of analyzing whether a 'change of interest' occurred among all the changed pixels resulting from many underlying factors (i.e., object motions, change of objects azimuth, appearance or disappearance of natural matters and appearance of mine).…”