Table 1 Our proposed method YOLO-UD is compared with other state-of-the-art methods. Where YOLO-UD-n is optimised over YOLO11n and others by analogy. The best results are highlighted in bold.

From: Enhanced feature representation for real time UAV image object detection using contextual information and adaptive fusion

Method

Person

Ped

Tri

Van

Truck

Awn

Car

Bus

Bicycle

Motor

Para/GFLOPS

FPS

mAP

YOLOX-tiny54

21.9

35.8

18.1

34.7

28.1

10.2

73.3

46.3

9.6

34.9

5.0M/6.45

243

31.3

YOLOX-s54

13.6

41.8

18.0

40.5

39.0

12.4

76.5

51.2

7.2

25.2

8.94M/26.8

188

32.5

YOLOv8n32

28.6

36.2

21.6

38.0

29.4

12.1

76.1

47.5

9.0

37.2

3.2M/8.7

208

33.5

YOLOv8s32

32.8

41.9

29.5

44.2

36.8

14.1

79.3

59.5

13.5

44.6

11.2M/28.6

182

39.6

YOLOv9s55

33.4

42.2

30.1

44.3

38.4

15.4

79.3

57.8

13.3

44.8

7.3M/27

190

39.9

YOLOv10n13

27.6

34.0

21.7

38.3

28.1

11.8

75.4

46.5

9.3

35.4

2.7M/8.2

229

32.8

YOLOv10s13

32.5

41.5

26.1

45.0

35.5

15.4

79.4

56.4

13.9

44.4

8.0M/24.5

188

39.0

YOLO11n33

28.6

36.2

21.0

39.1

28.6

11.3

76.4

46.9

9.1

38.8

2.6M/6.5

267

33.6

YOLO11s33

32.6

42.5

27.3

45.0

37.9

15.6

79.7

58.1

13.2

43.6

9.4M/21.5

196

39.5

YOLOv12n56

26.1

33.6

20.1

36.1

26.7

11.3

75.0

45.2

8.0

35.0

2.5M/5.8

232

31.7

YOLOv12s56

32.4

41.6

25.8

43.9

35.1

14.4

79.2

56.4

12.8

42.8

9.1M/19.3

188

38.4

AD-YOLO57

30.1

38.6

22.1

43.0

39.4

14.5

81.7

62.6

10.6

38.4

7.1M/19.2

122

38.1

EDGS-YOLOv858

-

-

-

-

-

-

-

-

-

-

4.2M/7.9

121

31.3

Li43

36.0

46.7

31.5

48.7

39.1

18.2

81.4

58.4

14.0

48.1

9.6M/-

167

42.2

MSA-YOLO59

17.3

33.4

14.8

41.5

41.4

18.4

76.8

60.9

11.2

31.0

-/-

-

34.7

UAV-YOLO20

22.9

39.4

20.5

42.1

45.3

20.7

79.8

61.2

16.4

36.8

7.46M/17.7

132

38.5

LE-YOLO60

39.1

46.7

24.5

43.1

31.4

13.8

82.3

52.9

12.0

46.8

2.1M/13.1

-

39.3

LUDY-n27

29.3

36.9

22.2

41.8

31.4

13.6

77.4

48.8

10.0

39.4

2.8M/-

218

35.2

LUDY-s27

34.3

44.8

29.8

48.4

39.4

16.9

80.9

62.2

14.5

46.2

10.4M/-

194

41.7

SPD-YOLOv861

-

-

-

-

-

-

-

-

-

-

-/-

-

41.0

FEYOLO62

29.0

36.6

21.2

41.2

31.5

12.6

77.5

49.2

10.2

39.5

6.3M/13.5

141

34.9

PSO-YOLO63

18.4

29.5

14.7

37.1

30.9

17.1

72.9

51.8

9.5

27.2

2.59M/29.0

-

30.9

YOLO-UD-n

36.6

47.1

25.2

43.6

31.8

13.8

81.0

55.3

14.2

46.1

3.3M/10.8

242

39.5

YOLO-UD-s

42.9

52.9

31.8

50.0

39.3

18.8

84.7

63.3

17.6

53.6

12.1M/29.8

194

45.5

Back to article page