agriculture

Closed

Crop Location Auto-Labeling Competition

隨著軟硬體的快速發展,近期人工智慧的應用成為顯學,並成功應用在廣泛領域上。然而,人工智慧在農業上的應用卻相當受限,除了作物生長周期長、資料不易大量累積外,也因為資料標註高度仰賴具有專業知識的農業專家,使得能作為機器學習的訓練資料集嚴重不足。空拍遙測影像,是在農業現場中相對容易取得的大量資料,透過衛星、飛機或熱氣球空拍等技術取得影像,得以推估耕地面積、作物種類,甚至研究氣候變遷下全球植被更迭等,但上述設備拍攝時間相當受限,也僅能獲取低解析度影像。近來無人機載重、飛行穩定性等技術逐漸成熟,主辦單位得以花費較短時間、以更高頻率拍攝高解析度的影像。呼應政府推動的五加二產業中「新農業」的發展,本競賽與經緯航太科技股份有限公司 (以下簡稱經緯航太公司) 共同合作,於臺灣北部水稻兩期作種植期間,以無人機拍攝水稻田數個時期高解析度影像,用以進行水稻植株位置辨識,未來期望能以人工智慧建立水稻田植株辨識模組,以提升臺灣未來農業發展軟實力。水稻植株辨識的實際應用,除了計算植株密度以進行水稻產量評估外,植株密度亦可搭配植生指標 (vegetative indices) 推估作物生育期或產期,或未來可應用在無人機定點少量噴灑植物保護劑的施作,達到節省成本及維持環境永續的雙重目的。此外也將從行政院農業委員會資料開放平台下載植物疫情發布等網路文字資料,期望能根據標註結果以人工智慧建立文字辨識分析模組。競賽將分三階段進行:第一階段依據訓練集影像資料進行不同階段水稻植株辨識,依測試集影像資料辨識準確度評分;第二階段依座談會(發想討論);第三階段依據訓練集文字資料進行相關標註或資訊擷取技術的應用方向。注意:本競賽頁面為第一階段水稻植株辨識。相關問題諮詢,請洽:aai.ntu.agri@outlook.com競賽論壇:水稻無人機全彩影像植株位置自動標註與應用競賽參賽對象全國各大專校院在學生(含研究生)全國高中職學生,因報名系統限制,高中學生報名時,請先以業界人士身分進行報名,待名次確認或獲獎時須提供在校證明,以便受獎。業界亦可參加,若名次在前 25% 且超過 baseline 之隊伍,經評審委員審定後,僅可獲頒計畫辦公室獎狀,無法受領教育部獎狀和獎金。競賽方式及評選辦法本競賽「水稻無人機全彩影像與農業訊息文字探勘辨識及應用」係依據主辦單位所提供之訓練集與測試集影像資料,並經由主辦單位聘僱之領域專家所標註的結果,以評比各參賽隊伍的準確度和名次,詳細辦法說明如下:本競賽包含影像和文字等不同類型之分項競賽。每項競賽都提供兩份資料集,分別為訓練集(Training Data)及測試集(Test Data)。以影像為例:訓練集包括 1. 水稻田區全彩 (RGB) 影像、2. 影像取得日期、3. 影像中所有植株中心位置;而測試集只有提供全彩 (RGB) 影像及影像取得日期。競賽將分三階段進行:第一階段依據訓練集影像進行辨識標註及資訊擷取比賽,依測試集資料辨識準確度評分。第二階段依座談會(發想討論),無提供獎金。第三階段依據訓練集文字資料進行相關標註、關聯植病分類等資訊擷取技術的應用方向。注意,三項比賽皆為獨立比賽。

2021-01-03T16:00:00+00:00 ~ 2021-06-18T15:59:59+00:00
Closed

愛文芒果不良品分類競賽

"Irwin Mango Defects Classification Competition" is registered hot! The highest bonus is 130,000 NTD! Welcome students from all disciplines and professionals to compete together to help Irwin Mango become the glory of Taiwan!In this competition, through establishing an image recognition algorithm model, five types of defects on mango are classified by images, which not only proposes a solution to this issue but also pictures the future of the Irwin mango industry.Irwin mango, one of Taiwan’s important agricultural exports, has continued to increase in sales in recent years and has even jumped to one of the three high-economy fresh fruit products for export. It has also expanded its export countries to Japan, China, the United States, and Hong Kong. Although in cooperation with the policies of local governments, Taiwanese mangoes have increased their reputation and expanded their market shares to the previous ones, they still encountered price-cutting competition from other mango exporting countries (Philippines, Thailand). Therefore, processing technology, brand marketing, and other works to enhance the value of products still need technological assistance to advance.After the “Irwin Mango Three Grades Classification Competition”, this competition will classify the five types of defects of Irwin mangoes, including latex adsorption, mechanical damage, anthracnose, poor coloration, black spots, and quickly identify the reason of defective products of Irwin mangoes through image recognition. We expect to analyze and forecast the mangoes by this data in the future, and provide producer information, reduce the rate of defective fruits of Irwin mango.Therefore, BIIC Lab cooperated with Walker Grow-Rite International Co., Ltd. to collect Irwin mango image data for several years. Through this competition, it will cultivate AI talents and establish an open and co-prosperous local database in Taiwan. By introducing the AI ​​image recognition technology with the concept of automation and precision, and using the database to establish an automatic mango sorting system in the future, we are eager to raise Taiwanese’ awareness of the agricultural industry upgrading, and refine Taiwan's local Irwin mango brand.For related questions, please contact: biiclab@ee.nthu.edu.tw Contest Forum: AI CUP 2020|愛文芒果影像辨識雙項競賽 討論區參賽對象具中華民國學籍學生(研究生亦可)。業界亦可參加,另列入綜合競賽敘獎排名。競賽獎金敘獎分為單項競賽獎金及綜合競賽獎金: 單項競賽獎金 五類不良品分類辨識競賽 (Defective Competition)第一名第二名第三名優等佳作(十名)10 萬元5 萬元3.5 萬元1 萬元十名,各 7.5 仟元敘獎對象為全學生隊伍,全隊隊員須為報名時具中華民國學籍之學生,敘獎時需檢附相關證明。兩種競賽前六名獲獎之全學生隊伍經評審委員審定後將獲教育部獎狀乙紙。各項獎勵名額得視參賽件數及成績酌予調整,參賽作品未達水準(官方公告之baseline)得由決選評審委員決定從缺,或不足額入選。 綜合競賽獎金 三類等級分類辨識競賽 (Grade Competition)第一名3 萬元 五類不良品分類辨識競賽 (Defective Competition)第一名3 萬元 雙項競賽綜合排名 (ORS) Overall Rating Score第一名第二名第三名10 萬元5 萬元3.5 萬元敘獎對象包含所有參賽之隊伍(業界及全學生隊伍,報名時隊伍中若包含一名以上業界人士,即視為業界隊伍)。ORS=0.4×(WAR in Grade Competition)+0.6×(WAR in Defective Competition)。本綜合競賽獎金由台灣瓦克國際股份有限公司提供。兩項競賽名次在前 25% 且超過 Baseline 之隊伍,經評審委員會審定後,將獲頒教育部人工智慧競賽計畫辦公室獎狀。各項獎勵名額得視參賽件數及成績酌予調整,參賽作品未達水準(官方公告之 baseline)得由決選評審委員決定從缺,或不足額入選。得獎隊伍之競賽報告將列入敘獎,該獎項將各頒發最佳報告獎獎狀乙紙。

2020-07-09T16:00:00+00:00 ~ 2021-01-25T15:59:59+00:00
Closed

愛文芒果等級分類競賽

「愛文芒果等級分類競賽」熱烈報名中!最高獎金 13 萬元!歡迎各科系學生、業界隊伍一起競爭,幫助愛文芒果成為台灣之光!本競賽透過建立影像辨識演算法模型,對愛文芒果影像進行三種等級分類,既提出本議題的解決方案,也描繪出大眾對愛文芒果產業未來樣貌的想像。台灣重要出口農產品之一的愛文芒果於近年銷量持續增長,不僅躍升為三大外銷高經濟生鮮果品之一,更將外銷國拓展至日本、中國、美國以及香港等地。雖然,在各國當地政府的政策配合下,台灣芒果較以往提高了知名度並拓展市佔率,卻還是遭遇其他同為芒果出口國(菲律賓、泰國)的削價競爭,因此諸多品種改良、採收後處理技術以及品牌行銷等提昇產品價值的工作,仍待科技輔助來推進。而其中亟待改善的是採收後處理技術。愛文芒果採收後依品質篩選為 A、B、C 三等級,依序為出口用、內銷用、加工用。然而愛文芒果依靠人工篩選,除了農村人口流失導致人力短缺,篩果流程也因保鮮期壓縮地極短,導致篩果階段約有 10% 的誤差,若以外銷金額估計,每年恐怕損失 1600 萬台幣。因此,BIIC Lab 與台灣瓦克國際股份有限公司合作,耗時數年收集愛文芒果影像資料,透過本競賽,培養 AI 人才,並建立開放共榮的台灣本地資料庫,希望於愛文芒果產業導入自動化、精準化概念的AI 影像辨識技術,在未來利用資料庫建立一套自動芒果篩果系統,並提升臺灣大眾對農業產業升級的意識,同時拉抬台灣本地愛文芒果的品牌精緻化。相關問題諮詢,請洽:biiclab@ee.nthu.edu.tw 競賽論壇: AI CUP 2020|愛文芒果影像辨識雙項競賽 討論區參賽對象具中華民國學籍學生(研究生亦可)。業界亦可參加,另列入綜合競賽敘獎排名。競賽獎金敘獎分為單項競賽獎金及綜合競賽獎金: 單項競賽獎金 三類等級分類辨識競賽 (Grade Competition)第一名第二名第三名優等佳作(十名)10 萬元5 萬元3.5 萬元1 萬元十名,各 7.5 仟元敘獎對象為全學生隊伍,全隊隊員須為報名時具中華民國學籍之學生,敘獎時需檢附相關證明。兩種競賽前六名獲獎之全學生隊伍經評審委員審定後將獲教育部獎狀乙紙。各項獎勵名額得視參賽件數及成績酌予調整,參賽作品未達水準(官方公告之baseline)得由決選評審委員決定從缺,或不足額入選。 綜合競賽獎金 三類等級分類辨識競賽 (Grade Competition)第一名3 萬元 五類不良品分類辨識競賽 (Defective Competition)第一名3 萬元 雙項競賽綜合排名 (ORS) Overall Rating Score第一名第二名第三名10 萬元5 萬元3.5 萬元敘獎對象包含所有參賽之隊伍(業界及全學生隊伍,報名時隊伍中若包含一名以上業界人士,即視為業界隊伍)。ORS=0.4×(WAR in Grade Competition)+0.6×(WAR in Defective Competition)。本綜合競賽獎金由台灣瓦克國際股份有限公司提供。兩項競賽名次在前 25% 且超過 Baseline 之隊伍,經評審委員會審定後,將獲頒教育部人工智慧競賽計畫辦公室獎狀。各項獎勵名額得視參賽件數及成績酌予調整,參賽作品未達水準(官方公告之baseline)得由決選評審委員決定從缺,或不足額入選。得獎隊伍之競賽報告將列入敘獎,該獎項將各頒發最佳報告獎獎狀乙紙。

2020-02-02T16:00:00+00:00 ~ 2020-12-29T15:59:59+00:00
Closed

Prediction of Milk yield of Taiwan Ranches

According to statistics, the expected revenue of global dairy is more than one hundred million US dollars[1], and in accordance with the data provided by DATA.COA[2], there are 557 dairy farms, 115,685 cows in Q2 2019, and that’s an average of 207 cows per farm. Date back to 2017, the annual report[3] showed that there were only 61,976 cows being bred and 419,342 tons of milk being produced. While digital transformation has became a trend, agriculture and cattle industry also start to embrace new technologies. Under the circumstance of downsizing, the average milk yield per cow in Taiwan has surpassed the average milk yield per cow in Australia, Germany and China...etc, and it is still increasing. The overall Taiwan dairy-strength are catching up the strength of the countries which have a highly developed dairy industry. (such as America and Israel… etc.)The goal of this issue is to predict the milk yield of Taiwan ranches in different regions by referring to the Dairy Herd Improvement, DHI dataset which is provided by Dairy Association Taiwan,R.O.C, hoping that these data can help grasping the key of milk yield forecasting, and thus benefits the dairy in Taiwan in the aspect of  Intellectual Management and pricing. AwardsThe first place 100,000 discount points of hicloudThe second place 50,000 discount points of hicloud The third place 50,000 discount points of hicloud honorable mention 50,000 discount points of hicloud (multiple winners, depends on the final result)Awards were provided by Chunghwa TelecomNote: 1.Hicloud points can redeem service charge. After the discount, the price will be charged at 30% off based on the list price automatically.2.Chunghwa Telecom deserves the right to make changes to the terms and conditions herein.The example of calculating points can be referred to https://aidea-web.tw/computing

2019-09-30T16:00:00+00:00 ~ 2019-12-18T15:59:59+00:00