&lt;title&gt;Training minimal artificial neural network architectures for subsoil object detection&lt;/title&gt;

Boese, Kenneth D.; Franklin, D E; Kahng, Andrew B.

doi:10.1117/12.211384

Cited by 1 publication

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Probing objectives in his work include Determination give upper and lower bounds on the number of probes needed to completely determine a particular object, Veri cation given an object description, bound the number of probes needed to verify the description, and Feature Determination given some object feature such a s o r i e n tation or convexity, b o u n d t h e n umberof probes needed to determine this feature. 7 Notice that if the scan is coarsened by a factor of k in each axis basically, looking at every k th coordinate value, we will require a factor of k 2 fewer probe operations to image the region. Associated image processing operations e.g., computing matrices of autocorrelations will typically enjoy similar speedups with the coarse scan.…”

Section: Sensors As Probesmentioning

confidence: 99%

“…When scanned across a region with maximum resolution, a single-point probe will yield an image of the region i.e., sensor returns at the integer lattice points. 7 If the single-point probe is scanned along a line, the e ect is that of a swept vehicle-mounted sensor or a hand-held detector that is swung in an arc. If we additionally threshold the sensor return, we obtain a so-called X-ray probe: such a probe returns the intersections of the line and all objects of interest Figure 3b.…”

Section: Sensors As Probesmentioning

confidence: 99%

See 1 more Smart Citation

<title>Distributed sensing and probing with multiple search agents: toward system-level landmine detection solutions</title>

1995

Self Cite

View full text Add to dashboard Cite

The problem of landmine detection has been studied for decades. Mine detection systems have t ypically been developed by rst identifying a sensor technology, then testing on particular manmade testbeds, then deploying the sensor on a vehicle or man-portable device. Despite much e ort, current systems still exhibit gaps between existing and desired capability, e.g., in terms of rate of advance, detection rate, and false alarm rate within demonstration testbeds. In this paper, we propose a new system-level approach to landmine detection. We argue that the landmine detection problem" cannot be attacked in a piecewise fashion: system-level solutions must simultaneously consider functional requirements, sensor technologies, models of sensors, the method of sensor application, and the platforms from which sensors are applied. This perspective allows us to shift our focus from the previous emphasis on novel sensor technology, and to go somewhat beyond traditional doctrines governing stando or man-portable detection. We rst propose a new theory of geometric sensing and probing in the mine detection context. Speci cally, w e propose new formulations of object identi cation by probing" which correspond to various sensing modalities. We demonstrate that multiple agents can achieve probe classes that are not serializable for emulation by a single probe agent. With this in mind, our second main contribution lies in proposing a new paradigm for landmine detection, based on i close-in observation with simple spectra, and ii small, inexpensive, networkable robotic sensing platforms which can act in a cooperative fashion to implement powerful multi-agent probing strategies.

show abstract

Section: Sensors As Probesmentioning

confidence: 99%

Section: Sensors As Probesmentioning

confidence: 99%