In this paper we present an adaptive incremental learning system for underwater mine detection and classification that
utilizes statistical models of seabed texture and an adaptive nearest-neighbor classifier to identify varied underwater
targets in many different environments. The first stage of processing uses our Background Adaptive ANomaly detector
(BAAN), which identifies statistically likely target regions using Gabor filter responses over the image. Using this
information, BAAN classifies the background type and updates its detection using background-specific parameters. To
perform classification, a Fully Adaptive Nearest Neighbor (FAAN) determines the best label for each detection. FAAN
uses an extremely fast version of Nearest Neighbor to find the most likely label for the target. The classifier perpetually
assimilates new and relevant information into its existing knowledge database in an incremental fashion, allowing
improved classification accuracy and capturing concept drift in the target classes. Experiments show that the system
achieves >90% classification accuracy on underwater mine detection tasks performed on synthesized datasets provided
by the Office of Naval Research. We have also demonstrated that the system can incrementally improve its detection
accuracy by constantly learning from new samples.
To protect naval and commercial ships from attack by terrorists and pirates, it is important to have automatic surveillance
systems able to detect, identify, track and alert the crew on small watercrafts that might pursue malicious intentions,
while ruling out non-threat entities. Radar systems have limitations on the minimum detectable range and lack high-level
classification power. In this paper, we present an innovative Automated Intelligent Video Surveillance System for Ships
(AIVS3) as a vision-based solution for ship security. Capitalizing on advanced computer vision algorithms and practical
machine learning methodologies, the developed AIVS3 is not only capable of efficiently and robustly detecting,
classifying, and tracking various maritime targets, but also able to fuse heterogeneous target information to interpret
scene activities, associate targets with levels of threat, and issue the corresponding alerts/recommendations to the man-in-
the-loop (MITL). AIVS3 has been tested in various maritime scenarios and shown accurate and effective threat
detection performance. By reducing the reliance on human eyes to monitor cluttered scenes, AIVS3 will save the
manpower while increasing the accuracy in detection and identification of asymmetric attacks for ship protection.
ATR in two dimensional images is valuable for precision guidance, battlefield awareness and surveillance
applications. Current ATR methods are largely data-driven and as a result, their recognition accuracy relies
on the quality of training dataset. These methods fail to reliably recognize new target types and targets in
new backgrounds and/or atmospheric conditions. Thus, there is a need for an ATR solution that can
constantly update itself with information from new data samples (samples may belong to existing classes,
background clutter or new target classes). In the paper, this problem is addressed in two steps: 1)
Incremental learning with Fully Adaptive Approximate Nearest Neighbor Classifier (FAAN) - A novel data
structure is designed to allow incremental learning in approximate nearest neighbor classifier. New data
samples are assimilated at reduced complexity and memory without retraining on existing data samples, 2)
Data Categorization using Data Effectiveness Measure (DEM) - DEM of a data sample is a degree to which
each sample belongs to a local cluster of samples. During incremental learning, DEM is used to filter out
redundant samples and outliers, thereby reducing computational complexity and avoiding data imbalance
issues. The performance of FAAN is compared with proprietary Bagging-based Incremental Decision Tree
(ABAFOR) implementation. Tests performed on Army ATR database with over 37,000 samples shows that
while classification accuracy of FAAN is comparable to ABAFOR (both close to 95%), the process of
incremental learning is significantly quicker.
Content-based video retrieval from archived image/video is a very attractive capability of modern intelligent video
surveillance systems. This paper presents an innovative Semantic-Based Video Indexing and Retrieval (SBVIR) software
toolkit to help users of intelligent video surveillance to easily and rapidly search the content of large video archives to
conduct video-based forensic and image intelligence. Tailored for maritime environment, SBVIR is suited for
surveillance applications in harbor, sea shores, or around ships. The system comprises two major modules: a video
analytic module that performs automatic target detection, tracking, classification, activities recognition, and a retrieval
module that performs data indexing, and information retrieval. SBVIR is capable of detecting and tracking objects from
multiple cameras robustly in condition of dynamic water background and illumination changes. The system provides
hierarchical target classification among a large ontology of watercraft classes, and is capable of recognizing a variety of
boat activities. Video retrieval is achieved with both query-by-keyword and query-by-example. Users can query video
content using semantic concepts selected from a large dictionary of objects and activities, display the history linked to a
given target/activity, and search for anomalies. The user can interact with the system and provide feedbacks to tune the
system for improved accuracy and relevance of retrieved data.
SBVIR has been tested for real maritime surveillance scenarios and shown to be able to generate highly-semantic
metadata tags that can be used during the retrieval to provide user with relevant and accurate data in real-time.
Building footprint extraction from GIS imagery/data has been shown to be extremely useful in various urban planning
and modeling applications. Unfortunately, existing methods for creating these footprints are often highly manual and
rely largely on architectural blueprints or skilled modelers. Although there has been quite a lot of research in this area,
most of the resultant algorithms either remain unsuccessful or still require human intervention, thus making them
infeasible for practical large-scale image processing systems. In this work, we present novel LiDAR and aerial image
processing and fusion algorithms to achieve fully automated and highly accurate extraction of building footprint. The
proposed algorithm starts with initial building footprint extraction from LiDAR point cloud based on an iterative
morphological filtering approach. This initial segmentation result, while indicating locations of buildings with a
reasonable accuracy, may however produce inaccurate building footprints due to the low resolution of the LiDAR data.
As a refinement process, we fuse LiDAR data and the corresponding color aerial imagery to enhance the accuracy of
building footprints. This is achieved by first generating a combined gradient surface and then applying the watershed
algorithm initialized by the LiDAR segmentation to find ridge lines on the surface. The proposed algorithms for
automated building footprint extraction have been implemented and tested using ten overlapping LiDAR and aerial
image datasets, in which more than 300 buildings of various sizes and shape exist. The experimental results confirm the
efficiency and effectiveness of our fully automated building footprint extraction algorithm.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.