Name
Abstract | ||
|---|---|---|
Detecting small objects is a challenging task. Existing CNN-based objection detection pipeline faces such a dilemma: using a high-resolution image as input incurs high computational cost, but using a low-resolution image as input loses the feature representation of small objects and therefore leads to low accuracy. In this work, we propose a cascade mask generation framework to tackle this issue. The proposed framework takes in multi-scale images as input and processes them in ascending order of the scale. Each processing stage outputs object proposals as well as a region-of-interest (RoI) mask for the next stage. With RoI convolution, the masked regions can be excluded from the computation in the next stage. The procedure continues until the largest scale image is processed. Finally, the object proposals generated from multiple scales are classified by a post classifier. Extensive experiments on Tsinghua-Tencent 100K traffic sign benchmark demonstrate that our approach achieves state-of-the-art small object detection performance at a significantly improved speed-accuracy tradeoff compared with previous methods. |
Year | Venue | Field |
|---|---|---|
2018 | ICME | Computer vision,Object detection,Pattern recognition,Task analysis,Computer science,Convolution,Feature extraction,Cascade,Artificial intelligence,Classifier (linguistics),Image resolution,Computation |
DocType | Citations | PageRank |
Conference | 1 | 0.35 |
References | Authors | |
0 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Guangting Wang | 1 | 16 | 3.22 |
| Zhiwei Xiong | 2 | 244 | 46.90 |
| Dong Liu | 3 | 721 | 74.92 |
| chong luo | 4 | 696 | 47.36 |