Home/Retail/Sneaker Occlusion Image Dataset

Sneaker Occlusion Image Dataset

V1.0
Latest Update:
2025-10-16
Samples:
15000 records
File Size:
0.8G
Format:
JPG/PNG/JSON
Data Domain:
Image
Holder:
MOBIUSI INCMOBIUSI INC
Industry Scope:
Product Recognition | Image Classification | E-commerce Search
Applications:
Object Detection | Image Segmentation | Feature Extraction

Brief Introduction

In the current retail e-commerce landscape, visual recognition systems face significant challenges due to occlusions affecting product visibility, which can lead to misclassification and poor user experience. Existing datasets often lack diverse occlusion scenarios, limiting the training effectiveness of machine learning models. This dataset aims to address these challenges by providing a comprehensive collection of images where sneakers are obscured by factors such as pant legs, blurred shoe tips, and ground reflections or mud. The data is collected using high-resolution cameras in various retail environments to ensure realistic conditions. Quality control measures include multiple rounds of annotation, consistency checks among annotators, and expert reviews to ensure high accuracy. The dataset is organized in JPG format, each image accompanied by metadata in a structured manner.

Sample Examples

ImageFile NameResolutionMain ColorBrand Logo VisibilityDegree Of OcclusionViewing AngleLighting ConditionsTexture ClarityBackground Clutter LevelShoe OrientationPresence Of ReflectionsDepth Of Field
208278fccb58e4ce737cecbb82087d68.jpg2080*961greenvisible2bottom viewindoorclear4frontno obvious reflectionshallow depth of field
68dc8942ebc101ca94043e15f8eeec5e.jpg1224*1632whitenot visible0topdim, possibly outdoorclear1front facing upno apparent reflectiondeep depth of field
0ce52da840f9bc1e6d7b4006f10f9af1.jpg1623*1279blackclearly visible0topbrightclearly discernible0frontno apparent reflectiondeep depth of field
b05a92a7df9b2d308c700576d1c635d6.jpg932*1748whiteclearly visible0topbrightclearly discernible1rightno apparent reflectionshallow depth of field
db4193d50f0ecee05600f2861939d803.jpg1632*1224burgundynot clear0top shotindoorclear5frontno reflectionshallow depth of field
f4a356beaaf1998a1ef0975e9f84de66.jpg900*1600whitepartially visible0topindoorclear2facing forwardslight reflectionshallow depth of field
43d6c29c19a487dd634b8fbae54d4932.jpg1885*1060graypartially visible0side viewbrightclear7facing leftnoneshallow depth of field
bbe5cbdbc850b72e9ebc312e26119792.jpg1632*1224blackclearly visible0from an oblique sideindoor, bright lightclearly discernible3left side forwardno apparent reflectiondeep depth of field
03e2ead5d45427935adda046b57c277c.png4368*2030greenclearly visible0side shotbrightclearly discernible0frontnonedeep depth of field
6fbf69cea40280438a8a3d31c6440020.jpg2610*1279grayclearly visible0side viewbrightclear0front facing leftnonedeep depth of field

Data Structure

FieldTypeDescription
file_namestringFile name
qualitystringResolution
dominant_colorstringThe main color of the sneakers in the image, indicated by a specific color name or color code
brand_logo_visibilitybooleanWhether the brand logo on the sneakers is clearly visible in the image
obstruction_levelintegerThe degree of occlusion of the sneakers in the image, ranging from 0 (no occlusion) to 10 (completely occluded)
angle_of_viewintegerThe viewing angle of the sneakers as shown in the image, such as from the front, side, or top
light_conditionstringThe lighting conditions when the image was taken, such as bright, cloudy, indoor, outdoor, etc.
texture_claritybooleanWhether the material texture of the sneakers is clearly distinguishable in the image
background_clutterintegerThe level of complexity in the image background, ranging from 0 (simple) to 10 (very complex)
shoe_orientationstringThe orientation of sneakers in the image, such as left, right, front, or back.
reflection_presencebooleanWhether there are noticeable reflections in the image, such as those on shiny surfaces.
depth_of_fieldstringThe degree of depth of field in the image, referring to the ratio of foreground and background sharpness, such as shallow or deep depth of field.

Compliance Statement

ItemContent
Authorization TypeCC-BY-NC-SA 4.0 (Attribution–NonCommercial–ShareAlike)
Commercial UseRequires exclusive subscription or authorization contract (monthly or per-invocation charging)
Privacy and AnonymizationNo PII, no real company names, simulated scenarios follow industry standards
Compliance SystemCompliant with China’s Data Security Law / EU GDPR / supports enterprise data access logs

Can't find the data you need?

Post a request and let data providers reach out to you.