Discriminating small extended targets at sea from clutter and other classes of boats in infrared and visual light imagery

Abstract

Operating in a coastal environment, with a multitude of boats of different sizes, detection of small extended targets is only one problem. A further difficulty is in discriminating detections of possible threats from alarms due to sea and coastal clutter, and from boats that are neutral for a specific operational task. Adding target features to detections allows filtering out clutter before tracking. Features can also be used to add labels resulting from a classification step. Both will help tracking by facilitating association. Labeling and information from features can be an aid to an operator, or can reduce the number of false alarms for more automatic systems.In this paper we present work on clutter reduction and classification of small extended targets from infrared and visual light imagery. Several methods for discriminating between classes of objects were examined, with an emphasis on less complex techniques, such as rules and decision trees. Similar techniques can be used to discriminate between targets and clutter, and between different classes of boats. Different features are examined that possibly allow discrimination between several classes. Data recordings are used, in infrared and visual light, with a range of targets including rhibs, cabin boats and jet-skis.

Video Processing From Electro-Optical Sensors for Object Detection and Tracking in a Maritime Environment: A Survey

“…growler, small boats, and debris) 100 km (ex. whales and icebergs) ⊗ Requires specialized user training Long range sensing ability ⊗ Suffers from minimum range Radar ∼ 1 km Detects objects with high radar cross-sections ⊗ Cannot penetrate water [6]− [10] to few (mostly metallic) ⊗ Cannot detect big objects with small radar cross-section [ Uses image processing/computer vision algorithms ⊗ Low range sensing due to atmospheric attenuation [11]− [30] Naturally intuitive, no need of user training ⊗ Difficult to detect far objects and predict their size and distance ⊗ Difficult to model water dynamics, wakes, and foam Longer range than visible range EO ⊗ Significantly poorer optics available ∼ m to Allows night vision ⊗ Saturated images in day time Infrared range…”

Extraction of small boat harmonic signatures from passive sonar

“…Table I describes the fundamental frequencies generated by a motor expressed in terms of engine speed, number of cylinders, gear ratio, number of blades, etc., which are fundamental frequencies of the tonals described in (2). In the previous sections the fundamental frequency c k was estimated and tracked through time using a Kalman filter, c KF;k .…”

“…The need for similar systems arises in the monitoring of harbor traffic for national security. There are many different methods for boat detection, examples including radar, 1 electro-optic (EO) and infrared (IR) cameras, 2 and both active and passive sonar. Active sonar and radar provide little additional information beyond detection.…”

Automatic detection of small surface targets with electro-optical sensors in a harbor environment

“…The horizon is used for stabilization, background estimation, separation between false detections above the horizon and surface targets below the horizon, and to compute features for classification [3].…”

“…The system should be able to detect and classify surface targets in maritime environments. Our system concept consists of an image processing chain [17], which includes components that perform image enhancement [14], automatic detection, clutter reduction and classification [3].…”