IEEE ICIP 2019 Grand Challenge

Mosquito Breeding Site Hunting
for Dengue Fever Control

In addition to this entrance, you can access the competition through “ICIP” menu on AIdea homepage (

Winners Announcement

1st place: Yuzheng Xu (score: 0.374227)
2nd place: Shang-Ying He (score: 0.321927)
3rd place: Po-Hao Hsu (score: 0.311144)

Challenge Description

Dengue fever is an acute infectious disease transmitted by mosquito. The peak time of dengue fever outbreak in Taiwan is usually at summertime. Mild clinical cases of dengue fever may present as symptoms such as fever, headaches, and myalgia while severe cases may have severe fluid leakage, hemorrhagic symptoms, shock, organ failure, coma and even death. The mortality rate can be as high as 20% or more if the patient does not receive proper treatment in time.

To effectively prevent dengue fever outbreak, cleaning up the breeding sites of the mosquitos is essential. Possible breeding sites for mosquitos include all containers that hold stagnant water, such as bottles, basins, buckets, cans, cups, bowls, tires, plastic bags, and etc.

Every year, the Taiwan Centers for Disease Control collaborate with local health department to examine the communities and to find uncleaned sites with those containers that may hold stagnant water, where may become mosquito breeding sites afterwards. However, the inspection takes tremendous manpower and time. This proposal provides labeled data for the various types of containers, and aims to build an object detection model for possible breeding sites. This way the inspectors can pinpoint the containers which hold stagnant water by digital camera images or live video, and thus improve the effectiveness of inspection and breeding site elimination.


The data provided by this topic are scenes of containers that may hold stagnant water, collected by the Taiwan Centers for Disease Control from 2008 to 2018. 75% of the data images have an aspect ratio of 400 x 300. There is a total training data of 2671 images and testing data of 2248 images. 23.7% of the testing data is used for the Public Leaderboard while the other 76.3% is used for the Private Leaderboard. Each image provides a labeled object and bounding boxes of the object.

Evaluation Criteria

Mean average precision (mAP) will be the criteria used for data evaluation. Each object is assessed and assigned an AP score, then all types of objects will be calculated for the average of their AP scores and finally result in the mAP score. The participants will be ranked according to the criteria.

Important Dates

  • 01 April 2019 | Registration opens
  • 27 May 2019 | Submission of accompanying paper for possible publication at ICIP 2019 (optional)
  • 01 June 2019 | Challenge submission due date
  • 15 June 2019 | Winners announcement
  • 01 July 2019 | Notification of acceptance of accompanying papers (optional)
  • 15 July 2019 | Camera ready accepted papers submission (optional)
  • 22-25 September 2019 | Presentation of accepted contributions to the Challenge, results and winners awards at ICIP 2019

Prize Information

1st 3000 USD
2nd 2000 USD
3rd 1000 USD
(tax included)

Host Organizations

Centers for Disease Control, Taiwan
Industrial Technology Research Institute, Taiwan


Hao-Yuan Cheng(CDC, Taiwan),
Li-Kang Shih(ITRI, Taiwan),

Additional Information

The challenge will be held on AIdea Artificial Intelligence Collaboration Platform.
Taiwan Centers for Disease Control will provide cash reward for top 3 teams.