18.6.3 Obstacle Detection, Time to Collision Techniques

Chapter Contents (Back)
Obstacle Detection. Collision Detection. Time to Collision.
See also Road, Path Following Operators.
See also Target Tracking, Collision Detection.
See also Airplane Obstacles, Collision Detection, Sense and Avoid.

Goodrich, G.W.[George W.],
Collision avoidance using optical pattern growth rate,
US_Patent4,257,703, 03/24/1981.
HTML Version. Basically looming. BibRef 8103

Sawhney, H.S., and Hanson, A.R.,
Trackability as a Cue for Potential Obstacle Identification and 3-D Description,
IJCV(11), No. 3, December 1993, pp. 237-265.
Springer DOI BibRef 9312
And: UMass-TR-92-15, February 1992. BibRef
Earlier:
Affine Trackability Aids Obstacle Detection,
CVPR92(418-424).
IEEE DOI BibRef
And:
Tracking, Detection and 3D Representation of Potential Obstacles Using Affine Constraints,
DARPA92(1009-1017). BibRef
Earlier:
Identification and 3D Description of 'Shallow' Environmental Structure in a Sequence of Images,
CVPR91(179-185).
IEEE DOI Shallow objects (mostly flat in depth), 3-D reconstructions and segmentation of the objects. BibRef

Sawhney, H.S.,
Simplifying Motion and Structure Analysis Using Planar Parallax and Image Warping,
ICPR94(A:403-408).
IEEE DOI BibRef 9400
And:
3D Geometry from Planar Parallax,
CVPR94(929-934).
IEEE DOI BibRef

Kumar, R., Sawhney, H.S., and Hanson, A.R.,
3D Model Acquisition from Monocular Image Sequences,
CVPR92(209-215).
IEEE DOI BibRef 9200
And: UMassCS-TR-93-5, January 1993. Extending the shallow structure work with refinement of the structure. BibRef

Sawhney, H.S., Kumar, R., and Hanson, A.R., Riseman, E.M.,
Landmark-Based Navigation-Model Extension and Refinement,
UMass-CS-TR-93-6, January 1993.
See also Landmark-Based Navigation and the Acquisition of Environmental Models. BibRef 9301
And:
Model Extension and Refinement Using Landmarks,
DARPA93(507-514). BibRef

Kumar, R.,
Model Dependent Inference of 3D Information from a Sequence of 2D Images,
COINS- TR-92-04, 1992, BibRef 9200 Ph.D. BibRef

Ringach, D.L., and Baram, Y.,
A Diffusion Mechanism for Obstacle Detection from Size-Change Information,
PAMI(16), No. 1, January 1994, pp. 76-80.
IEEE DOI Obstacles are indicated by the size change effects. BibRef 9401

Meyer, F.G.,
Time-to-Collision from First-Order Models of the Motion Field,
RA(10), 1994, pp. 792-798. BibRef 9400

Meyer, F., Bouthemy, P.,
Estimation of Time-to-Collision Maps from First Order Motion Models and Normal Flows,
ICPR92(I:78-82).
IEEE DOI BibRef 9200

Ancona, N.[Nicola], Poggio, T.[Tomaso],
Optical Flow from 1-D Correlation: Application to a Simple Time-to-Crash Detector,
IJCV(14), No. 2, March 1995, pp. 131-146.
Springer DOI BibRef 9503
Earlier: ICCV93(209-214).
IEEE DOI BibRef
And: MIT AI Memo-1375, October 1993.
WWW Link. BibRef
And: Add A2 Horn, B.K.P., DARPA93(673-682). Computations only in 1-D. BibRef

Ancona, N.,
A Fast Obstacle Detection Method Based on Optical Flow,
ECCV92(267-271).
Springer DOI BibRef 9200

Hatsopoulos, N., Gabbiani, F., and Laurent, G.,
Elementary Computation of Object Approach by a Wide-Field Visual Neuron,
Science(270), November 10, 1995, pp. 1000-1003. Has the standard references to biological issues in optical flow and related topics. Not computer vision, but in a locust, a neuron's response is described by multiplying the velocity of the image edge with an exponential function of the size of the object's image on the retina. The product peaks before impact, thus the locust can anticipate collision. BibRef 9511

Burlina, P.[Philippe], and Chellappa, R.[Rama],
Analyzing Looming Motion Components from Their Spatiotemporal Spectral Signature,
PAMI(18), No. 10, October 1996, pp. 1029-1033.
IEEE DOI 9611
Time to Collision. BibRef
Earlier:
Spectral and Temporal Representations of Looming and Maneuvering Information,
ARPA94(II:1199-1207). BibRef
And:
Spatio-temporal moments and generalized spectral analysis of divergent images for motion estimation,
ICIP94(I: 328-332).
IEEE DOI 9411
BibRef
And:
Time-to-X: Analysis of Motion through Temporal Parameters,
CVPR94(461-468).
IEEE DOI BibRef
And:
Virtually Observable Temporal Kinematic Descriptors for Polynomial Translations,
DraftTracking vehicle motions (i.e. limited motions). BibRef

Santos-Victor, J., Sandini, G.,
Uncalibrated Obstacle Detection Using Normal Flow,
MVA(9), No. 3, 1996, pp. 130-137.
Springer DOI 9611
BibRef

Borenstein, J., Koren, Y.,
The Vector Field Histogram: Fast Obstacle Avoidance for Mobile Robots,
RA(7), 1991, pp. 278-288. BibRef 9100

Borenstein, J., Koren, Y.,
Histogramic In-Motion Mapping for Mobile Robot Obstacle Avoidance,
RA(7), 1991, pp. 535-539. BibRef 9100

Young, G.S., Herman, M., Hong, T.H., Jiang, D., Yang, J.C.S.,
New Visual Invariants for Terrain Navigation without 3D Reconstruction,
IJCV(28), No. 1, June 1998, pp. 45-71.
DOI Link 9807
BibRef

Young, G.S., Hong, T.H., Herman, M., Yang, J.C.S.,
New Visual Invariants for Obstacle Detection Using Optical Flow Induced from General Motion,
WACV92(100-109).
IEEE DOI BibRef 9200

Vemuri, B.C., Chen, L., Vu-Quoc, L., Zhang, X., Walton, O.,
Efficient and Accurate Collision Detection for Granular Flow Simulation,
GMIP(60), No. 6, November 1998, pp. 403-422. BibRef 9811

Yamaguchi, H.[Hideaki], Kasano, A.[Akira],
Method and apparatus for detecting an approaching object within a monitoring zone,
US_Patent5,798,787, Aug 25, 1998
WWW Link. BibRef 9808

Weisser, H.[Hubert],
Method for measuring visibility from a moving vehicle,
US_Patent5,987,152, Nov 16, 1999
WWW Link. BibRef 9911

Raviv, D.[Daniel], Joarder, K.[Kunal],
The Visual Looming Navigation Cue: A Unified Approach,
CVIU(79), No. 3, September 2000, pp. 331-363. 0008

DOI Link BibRef
Earlier: A2, A1:
A Novel Method to Calculate Looming Cue for Threat of Collision,
SCV95(341-346).
IEEE DOI BibRef
And: A2, A1:
A New Method to Calculate Looming for Autonomous Obstacle Avoidance,
CVPR94(777-780).
IEEE DOI Florida Atlantic University. Relative change in irradiance in the image to get the change in relative size. Study texture and change around the fixated point. BibRef

Galbraith, J.M., Kenyon, G.T., Ziolkowski, R.W.,
Time-to-Collision Estimation from Motion Based on Primate Visual Processing,
PAMI(27), No. 8, August 2005, pp. 1279-1291.
IEEE Abstract. 0506
Extract velocity features, similar to, but different from, optical flow. BibRef

Stein, G.P.[Gideon P.],
System and method for detecting obstacles to vehicle motion and determining time to contact therewith using sequences of images,
US_Patent7,113,867, Sep 26, 2006
WWW Link. BibRef 0609

Stein, G.P.[Gideon P.],
System and method for generating a model of the path of a roadway from an image recorded by a camera,
US_Patent7,151,996, Dec 19, 2006
WWW Link. BibRef 0612

Chessa, M.[Manuela], Solari, F.[Fabio], Sabatini, S.P.[Silvio P.],
Adjustable linear models for optic flow based obstacle avoidance,
CVIU(117), No. 6, June 2013, pp. 603-619.
Elsevier DOI 1304
BibRef
Earlier: A1, A3, A2:
A Fast Joint Bioinspired Algorithm for Optic Flow and Two-Dimensional Disparity Estimation,
CVS09(184-193).
Springer DOI 0910
Motion interpretation; Affine description; Recursive filtering; Kalman filter; Time-to-contact; Surface orientation; Biologically inspired vision BibRef

Rahadianti, L.[Laksmita], Jeong, W.[Wooseong], Sakaue, F.[Fumihiko], Sato, J.[Jun],
Time-to-Contact in Scattering Media,
IEICE(E100-D), No. 3, March 2017, pp. 564-573.
WWW Link. 1703
Photometric information rather than geometric. BibRef

Seo, S.Y.[Su-Young],
Estimation of edge displacement against brightness and camera-to-object distance,
IET-IPR(11), No. 8, August 2017, pp. 568-577.
DOI Link 1708
BibRef

Xing, L.J.[Lin-Jie], Yu, K.[Kailong], Yang, Y.[Yang],
Target Positioning for Complex Scenes in Remote Sensing Frame Using Depth Estimation Based on Optical Flow Information,
RS(15), No. 4, 2023, pp. xx-yy.
DOI Link 2303
BibRef

Fedorishin, D.[Dennis], Mohan, D.D.[Deen Dayal], Jawade, B.[Bhavin], Setlur, S.[Srirangaraj], Govindaraju, V.[Venu],
Hear The Flow: Optical Flow-Based Self-Supervised Visual Sound Source Localization,
WACV23(2277-2286)
IEEE DOI 2302
Location awareness, Image motion analysis, Visualization, Image databases, Multimedia Web sites, Self-supervised learning BibRef

Sperling, M., Bouteiller, Y., de Azambuja, R., Beltrame, G.,
Domain Generalization via Optical Flow: Training a CNN in a Low-Quality Simulation to Detect Obstacles in the Real World,
CRV20(117-124)
IEEE DOI 2006
sim2real, optical flow, domain generalization BibRef