Week 8 : Web-Assisted Object Detection

WEEK 8:

WEB-ASSISTED OBJECT

DETECTION

A L E J A N D R O TO R R O E L L A &

AM

I R R . ZA M

I R

GEOMETRY METHOD PROCEDURE

For each query image we manually set orientation, angle of view, range of view, and location of camera.

: Camera location

: Object locations

: Field of vision

GEOMETRY METHOD PROCEDUREUsing the obtained FOV, select only the objects that are within the

FOV

Calculate the degrees from the left limit of the FOV and store in a vector specific to the object’s class These vectors will be

our “true” layout of objects.

.

.

.

GEOMETRY METHOD PROCEDUREWe then run our DPM detectors for the classes in question on the

query image.

Below are results for Street Lights (green) and Traffic Signals (red).

GEOMETRY METHOD PROCEDUREWe sift through the detections that completely disagree with the

“true” GIS layout.

GEOMETRY METHOD PROCEDUREWe then sift through the detections again by size of bounding boxes

(too large or too small)

GEOMETRY METHOD PROCEDUREUsing the sifted bounding boxes we generate all possible

combinations (no repeats, order doesn’t matter) of possible layouts.

For each class: Out of the N detections, choose k of them for the possible layout. Where

For each layout combination we calculate the “cost” of it compared to the obtained “true” GIS layout and keep track of the combination that returned the minimum

Two cost functions we’ve tested:

Absolute value:

Standard deviation:

GEOMETRY METHOD PROCEDUREOnce we’ve traversed through all the possible combinations, we

display the detections that resulted in the minimum of the cost function.

𝑆𝑇𝐷

𝐴𝐵𝑆

GEOMETRY METHOD RESULTS: BEFORE

𝑆𝑇𝐷

Traffic SignalsTrash CansTraffic Signs

GEOMETRY METHOD RESULTS: AFTER GIS SIFT

𝑆𝑇𝐷


GEOMETRY METHOD RESULTS: AFTER SIZE SIFT

𝑆𝑇𝐷


GEOMETRY METHOD RESULTS: AFTER FUSION (ABS)

𝑆𝑇𝐷


GEOMETRY METHOD RESULTS: AFTER FUSION (STD)

𝑆𝑇𝐷



𝑆𝑇𝐷

Traffic SignalsStreet Lights


𝑆𝑇𝐷



𝑆𝑇𝐷



𝑆𝑇𝐷



𝑆𝑇𝐷



𝑆𝑇𝐷

Street LightsTraffic Signs


𝑆𝑇𝐷



𝑆𝑇𝐷



𝑆𝑇𝐷



𝑆𝑇𝐷



𝑆𝑇𝐷



𝑆𝑇𝐷



𝑆𝑇𝐷



𝑆𝑇𝐷



𝑆𝑇𝐷



𝑆𝑇𝐷



𝑆𝑇𝐷



𝑆𝑇𝐷



𝑆𝑇𝐷



𝑆𝑇𝐷



𝑆𝑇𝐷

Fire HydrantsStreet Lights


𝑆𝑇𝐷



𝑆𝑇𝐷



𝑆𝑇𝐷



𝑆𝑇𝐷



𝑆𝑇𝐷



𝑆𝑇𝐷



𝑆𝑇𝐷



𝑆𝑇𝐷



𝑆𝑇𝐷



𝑆𝑇𝐷

Traffic SignalsTraffic Signs


𝑆𝑇𝐷



𝑆𝑇𝐷



𝑆𝑇𝐷



𝑆𝑇𝐷


GEOMETRY METHOD CONCLUSIONS

• Using the Standard deviation cost function resulted in better results compared to the Absolute value function on average.• A more advanced cost function would probably result in

even better results• Results look promising considering we haven’t implemented a

robust sensor model for creating the “true” GIS layout

GOALS FOR NEXT WEEK

• Implement a robust sensor model• Look into more advanced cost functions• Instead of crudely sifting through the bounding boxes by size

using a threshold based on the size of the image, use the distances of the objects from the camera to estimate how large the bounding box should be.

THANK YOUFIN.

Week 8 : Web-Assisted Object Detection

Documents

true gis layout

street lights green

query image

location of camera

camera location

object locations

obtained fov

range of view