AI Paper Atlas

Research map / Detection and segmentation / CNN features

Constellation Dataset: Benchmarking High-Altitude Object Detection for an Urban Intersection

Mehmet Kerem Türkcan, Chengbo Zang, Sanjeev Narasimhan, Gyung Hyun Je, Bo Yu, Mahshid Ghasemi, Javad Ghaderi, Gil Zussman, Zoran Kostić

IJCV 2026 · Detection and segmentation › CNN features · approach: Box regression and loss design · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
train at 2x input resolution (bilinear upscaling)YOLOv8x · Constellation testmAP@0.5: 93.0 -> 94.8Improved
add Real-ESRGAN super-resolution to 2x trainingYOLOv8x (2x) · Constellation testmAP@0.5: 94.8 -> 95.0Improved
add Real-ESRGAN super-resolution to 2x trainingYOLOv8n (2x) · Constellation testmAP@0.5: 94.8 -> 94.2Hurt
use P2-P6 detection layers instead of default P3-P5YOLOv8x · Constellation testmAP@0.5: 93.0 -> 94.3Improved
add P2 detection layerYOLOv8x · Constellation testmAP@0.5: 93.0 -> 94.0Improved
add P6 detection layerYOLOv8x · Constellation testmAP@0.5: 93.0 -> 94.0Improved
pretrain on VisDrone in addition to COCO (ablation)YOLOv8x · Constellation test (no augmentation)mAP@0.5: 93.0 -> 94.8Improved
pretrain on CARLA synthetic data in addition to COCO (ablation)YOLOv8x · Constellation test (with augmentation)mAP@0.5: 94.7 -> 94.4Hurt
pretrain on Stanford Drone Dataset in addition to COCO (ablation)YOLOv8x · Constellation test (no augmentation)mAP@0.5: 93.0 -> 93.0No clear effect
use pretraining (COCO) instead of random initialization with augmentation (ablation)YOLOv8x · Constellation test (with augmentation)mAP@0.5: 94.7 vs 94.7No clear effect
add custom weather augmentations (MotionBlur, RandomShadow, RandomRain) (ablation)YOLOv8x COCO · Constellation testmAP@0.5: 93.0 -> 94.7Improved
add custom augmentations to VisDrone-pretrained model (ablation)YOLOv8x COCO+VisDrone · Constellation testmAP@0.5: 94.8 -> 95.4Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy