Skip to main content

AV dataset exploration-extended

Created on August 18|Last edited on August 19

Artifact Table



00e9be89-00001070.jpg
00e9be89
00001070
bdd1k
1
1
0
1
0
1
0
08008acf-4c0db435.jpg
08008acf
4c0db435
bdd1k
1
1
1
1
1
1
0
65cf107a-65604012.jpg
65cf107a
65604012
bdd1k
1
1
1
1
1
1
0
2d89f625-5e44c56a.jpg
2d89f625
5e44c56a
bdd1k
1
0
0
0
0
1
0
File_Name
P1
P2
Images
Dataset
background
road
traffic light
traffic sign
person
vehicle
bicycle
1
2
3
4
5
6
7
8
9
10
11



P1 Attiribute


File_Name
P2
Images
Dataset
background
road
traffic light
traffic sign
person
vehicle
bicycle
1
00e9be89
2
08008acf
3
65cf107a
4
2d89f625
5
6b9077b7
P1
Images with same p1 attribute appear to be similar, this should considered when splitting the dataset between training



Model's Bicycle Class Detection


File_Name
P1
P2
Images
Dataset
background
road
traffic light
traffic sign
person
vehicle
1
0
2
1
bicycle
Bicycles are rare and small, it maybe hard for our models to learn this class.



Person and Traffic light/sign

P1 Attribute


File_Name
P1
Images
road
traffic light
traffic sign
person
vehicle
bicycle
1
00000000
2
00000280
3
00000305
4
00000415
5
00000425
P2



P2 Attribute


File_Name
P1
Images
road
traffic light
traffic sign
person
vehicle
bicycle
1
00000000
2
00000280
3
00000305
4
00000415
5
00000425
P2
Focused on evaluating the distribution of detected objects based on the 'p1' and 'p2' attribute. By filtering the 'person' column with a value of 1, 'traffic light' column with a value of 0.8, and 'traffic sign' column with a value of 0.8, aimed to identify instances of person detection. Analysis revealed that a significant number of persons were detected in close proximity to both traffic lights and traffic signs.
Among the collected images, a total of 351 were classified as containing persons. Notably, when we refined the data by selecting images where the 'traffic light' score was equal to or exceeded 0.8, and the 'traffic sign' score was equal to or exceeded 0.8, the image count reduced to 225. This suggests that a substantial proportion of person detections occur in situations involving high-confidence traffic light and traffic sign recognition. This strong correlation indicates that our model is particularly effective at detecting individuals near these two distinct features on the road, suggesting its potential to enhance safety around such critical elements.



Group By Aggregations


traffic light
traffic sign
person
bicycle
1
1
vehicle

traffic light
traffic sign
person
vehicle
1
1
bicycle

traffic light
traffic sign
vehicle
bicycle
1
1
person

Training Results


Run set
30

File<(table)>
File<(table)>
File<(table)>
File<(table)>
File<(table)>
File<(table)>
File<(table)>
File<(table)>